Multimodal keyphrase generation (MKP) aims to extract a concise set of keyphrases that capture the essential meaning of paired image–text inputs, enabling structured understanding, indexing, and retrieval of multimedia data across the web and social platforms. Success in this task demands effectively bridging the semantic gap between heterogeneous modalities. While multimodal large language models (MLLMs) achieve superior cross-modal understanding by leveraging massive pretraining on image-text corpora, we observe that they often struggle with modality bias and fine-grained intra-modal feature extraction. This oversight leads to a lack of robustness in real-world scenarios where multimedia data is noisy, along with incomplete or misaligned modalities. To address this problem, we propose AimKP, a novel framework that explicitly reinforces intra-modal semantic learning in MLLMs while preserving cross-modal alignment. AimKP incorporates two core innovations: (i) Progressive Modality Masking, which forces fine-grained feature extraction from corrupted inputs by progressively masking modality information during training; (ii) Gradient-based Filtering, that identifies and discards noisy samples, preventing them from corrupting the model’s core cross-modal learning. Extensive experiments validate AimKP’s effectiveness in multimodal keyphrase generation and its robustness across different scenarios.

Speech translation (ST) aims to translate speech from a source language into text in the target language. Naturally, speech signals contain paralinguistic cues beyond linguistic content, which could influence or even alter the interpretation of a lexically identical sentence, thereby yielding distinct translations. However, existing ST models lack direct and sufficient modeling of paralinguistic information, which limits their ability to perceive paralinguistic cues and understand speech comprehensively, leading to degraded translation performance. In response, we propose Paralinguistic-aware Speech Translation (PLaST), a novel dual-branch framework which directly leverages paralinguistic cues beyond the linguistic content. Specifically, PLaST employs a speech encoder and a style extractor to independently generate linguistic and paralinguistic representations, respectively. To obtain a purified linguistic representation aligned with the text representation, a hierarchical Optimal Transport (OT) is applied on the layer-wise outputs from an LLM decoder. Then, the paralinguistic information is retrieved and refined with an Attention-based Retrieval (AR) module, with the linguistic representation serving as queries to enable joint guidance for semantic understanding and translation generation. PLaST outperforms the strong baseline with an average of 5.0 directional and 4.5 global contrastive likelihood scores on the paralinguistic-sensitive benchmark ContraProST, demonstrating its superior capability in paralinguistic perception. Further experiments on the standard speech translation benchmark CoVoST-2 show that PLaST generalizes well to typical ST scenarios.

Critical thinking is essential for building robust AI systems, preventing them from blindly accepting flawed data or biased reasoning. However, prior work has primarily focused on passive critical thinking, where models simply reject problematic queries without taking constructive steps to address user requests. In this work, we introduce proactive critical thinking, a paradigm where models actively seek missing or clarifying information from users to resolve their queries better. To evaluate this capability, we present GSM-MC and GSM-MCE, two novel benchmarks based on GSM8K for assessing mathematical reasoning under incomplete or misleading conditions. Experiments on Qwen3 and Llama series models show that, while these models excel in traditional reasoning tasks, they struggle with proactive critical thinking, especially smaller ones. However, we demonstrate that reinforcement learning (RL) can significantly improve this ability. By incorporating heuristic information into the reward function, we achieve substantial gains, boosting the Qwen3-1.7B's accuracy from 0.15% to 73.98% on GSM-MC. We hope this work advances models that collaborate more effectively with users in problem-solving through proactive critical thinking.

Zerui Chen, Qinggang Zhang, Zhishang Xiang, Zhimin Wei, Linfeng Gao, Xiao Huang, Zhihong Zhang, Jinsong Su. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Sign language translation (SLT) converts continuous sign videos into spoken-language text, yet it remains challenging due to the intrinsic modality mismatch between visual signs and written text, particularly in gloss-free settings.Recent SLT systems increasingly adopt CLIP-like Vision-Language pretraining (VLP) for cross-modal alignment, but the random inbatch contrast provides few, batch-dependent negatives and may mislabel semantically similar (or even identical) pairs as negatives, introducing noisy and potentially inconsistent alignment supervision.In this work, we first conduct a preliminary trajectory-based analysis that tracks negative video-text similarity over training.The results show that only a small subset of negatives exhibits the desired behavior of being consistently pushed away, while the remaining negatives display heterogeneous and often non-decreasing similarity dynamics, suggesting that random in-batch negatives are frequently uninformative for effective alignment.Inspired by this, we propose Selective Contrastive Learning for SLT (SCL-SLT) with a Pair Selection (PS) strategy.PS scores candidate negatives using similarity dynamics from reference checkpoints and constructs mini-batches via a curriculum that progressively emphasizes more challenging negatives, thereby strengthening contrastive supervision while reducing the influence of noisy or semantically invalid negatives.

Zhanyu Liu, Qingguo Hu, Ante Wang, Chenqing Liu, Zhishang Xiang, Hui Li, Delai Qiu, Jinsong Su. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zhiwen Ruan, Yichao Du, Jianjie Zheng, Longyue Wang, Yun Chen, Peng Li, Jinsong Su, Yang Liu, Guanhua Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

The effective detection and governance of Large Language Model (LLM) generated content has become increasingly critical due to the growing risk of misuse. Despite the impressive performance of existing detectors, their reliability and potential in multilingual, real-world scenarios remain largely underexplored.In this study, we introduce DetectRL-X, a comprehensive multilingual benchmark designed to evaluate advanced detectors across 8 dimensions. The benchmark encompasses 8 languages commonly used in commercial contexts and collects human-written texts from 6 domains highly susceptible to LLM misuse. To better aligned with real-world applications, We create LLM-generated texts using 4 popular commercial LLMs, and include typical AI-assisted writing operations such as polishing, expanding, and condensing to capture authentic usage patterns. Furthermore, we develop a multilingual framework for paraphrasing and perturbation attacks to simulate diverse human modifications and writing noise, enabling stress testing of detectors across languages.Experimental results on DetectRL-X reveal the strengths and limitations of current state-of-the-art detectors when applied to diverse linguistic resources. We further analyze how domains, generators, attack strategies, text length, and refinement operations influence performance in different languages, underscoring DetectRL-X as an effective benchmark for strengthening multilingual and language-specific detectors.

Sign language research has achieved significant progress due to the advances in large language models (LLMs). However, the intrinsic ability of LLMs to understand sign language, especially in multimodal contexts, remains underexplored. To address this limitation, we introduce \textbf{CNSL-bench}, the first comprehensive \textbf{C}hinese \textbf{N}ational \textbf{S}ign \textbf{L}anguage \textbf{bench}mark designed for evaluating multimodal large language models (MLLMs) in sign language understanding. The proposed CNSL-bench is characterized by: 1) Authoritative grounding, as it is anchored to the officially standardized \textit{National Common Sign Language Dictionary}, mitigating ambiguity from regional or non-canonical variants and ensuring consistent semantic definitions; 2) Multimodal coverage, providing aligned textual descriptions, illustrative images, and sign language videos; and 3) Articulatory diversity, supporting fine-grained analysis across key manual articulatory forms, including air-writing, finger-spelling, and the Chinese manual-alphabet. Using CNSL-bench, we extensively evaluate 21 open-source and proprietary up-to-date MLLMs. Our results reveal that, despite recent advances in multimodal modeling, current MLLMs remain substantially inferior to human performance, exhibiting systematic disparities across input modalities and manual articulatory forms. Additional diagnostic analyses suggest that several performance limitations persist beyond improvements in reasoning and that instruction-following robustness varies substantially across models.

Recent research suggests that tree search algorithms (e.g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks. However, they often require more than 10 times the computational resources of greedy decoding due to wasteful search strategies, making them difficult to be deployed in practical applications. This study introduces a novel guided tree search algorithm with a goal-directed heuristic function and node-level exploration budget (maximum number of children) calculation to tackle this issue. By considering the search progress towards the final answer (history) and the guidance from a value network (future) trained without any step-wise annotations, our algorithm iteratively selects the most promising tree node before expanding it within the boundaries of the allocated computational budget. Experiments conducted on the GSM8K, TabMWP, and MATH datasets demonstrate that our method not only offers competitive performance but also enjoys significantly lower computational costs compared to baseline methods.

Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs), but at the cost of increased computational resources. In this work, we identify two key challenges contributing to this inefficiency: \textit{over-exploration} due to redundant states with semantically equivalent content, and \textit{under-exploration} caused by high variance in verifier scoring leading to frequent trajectory switching. To address these issues, we propose FETCH – an e{\bf f}fici{\bf e}nt {\bf t}ree sear{\bf ch} framework, which is a flexible, plug-and-play system compatible with various tree search algorithms.Our framework mitigates over-exploration by merging semantically similar states using agglomerative clustering of text embeddings obtained from a fine-tuned SimCSE model. To tackle under-exploration, we enhance verifiers by incorporating temporal difference learning with adjusted \lambda-returns during training to reduce variance, and employing a verifier ensemble to aggregate scores during inference. Experiments on GSM8K, GSM-Plus, and MATH datasets demonstrate that our methods significantly improve reasoning accuracy and computational efficiency across four different tree search algorithms, paving the way for more practical applications of LLM-based reasoning. The code is available at https://github.com/DeepLearnXMU/Fetch.

Direct speech translation (ST) has garnered increasing attention nowadays, yet the accurate translation of terminology within utterances remains a great challenge. In this regard, current studies mainly concentrate on leveraging various translation knowledge into ST models. However, these methods often struggle with interference from irrelevant noise and can not fully utilize the translation knowledge. To address these issues, in this paper, we propose a novel Locate-and-Focus method for terminology translation. It first effectively locates the speech clips containing terminologies within the utterance to construct translation knowledge, minimizing irrelevant information for the ST model. Subsequently, it associates the translation knowledge with the utterance and hypothesis from both audio and textual modalities, allowing the ST model to better focus on translation knowledge during translation. Experimental results across various datasets demonstrate that our method effectively locates terminologies within utterances and enhances the success rate of terminology translation, while maintaining robust general translation performance.

Recent studies have explored Continual Instruction Tuning (CIT) in Multimodal Large Language Models (MLLMs), with a primary focus on Task-incremental CIT, where MLLMs are required to continuously acquire new tasks.However, the more practical and challenging Domain-incremental CIT, focused on the continual adaptation of MLLMs to new domains, remains underexplored.In this paper, we propose a new Sparse Mixture of Expert (SMoE) based method for domain-incremental CIT in MLLMs.During training, we learn a domainspecific SMoE module for each new domain in every FFN sub-layer of MLLMs, preventing catastrophic forgetting caused by inter-domain conflicts.Moreover, we equip the SMoE module with a domain-specific autoregressive loss (DSAL), which is used to identify the most suitable SMoE module for processing each test instruction during inference.To further enhance the SMoE module's ability to learn domain knowledge, we design an adaptive thresholdbased router (AT-Router) that allocates computing resources (experts) to instruction tokens based on their importance.Finally, we establish a new benchmark to evaluate the efficacy of our method and advance future research.Extensive experiments show that our method consistently outperforms all competitive baselines.

Qinggang Zhang, Zhishang Xiang, Yilin Xiao, Le Wang, Junhui Li, Xinrun Wang, Jinsong Su. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

The few-shot relation extraction (FSRE) aims at enhancing the model's generalization to new relations with a few labeled instances.Existing studies usually adopt prototype networks (Pro-toNets) for FSRE and assume that the support set, adapting the model to new relations, only contains accurately labeled support instances.However, this assumption is often unrealistic, as even carefully-annotated datasets commonly contain mislabeled instances.In this paper, we first conduct a preliminary study that reveals the high sensitivity of ProtoNets to noisy labels in the support set.Moreover, we find that fully leveraging mislabeled support instances is crucial for enhancing the FSRE model robustness.Thus, we propose a self-denoising model for FSRE, designed to improve model robustness by automatically correcting mislabeled support instances.It comprises two core components: 1) a label correction module (LCM), used to correct noisy labels of support instances based on the distances between them in the embedding space, and 2) a relation classification module (RCM), aimed to achieve more accurate predictions for new relations based on the corrected labels produced by LCM.Moreover, we propose a feedback-based training strategy, which focuses on training LCM and RCM to synergistically handle noisy labels in support set.Experimental results on two public datasets confirm the robustness of our model.Particularly, even in scenarios without noisy labels, our model significantly outperforms all baselines.

The widespread adoption of large language models (LLMs) has increased the need for reliable AI-text detection.While current detectors perform well on benchmark datasets, we highlight a critical vulnerability: increasing the temperature parameter during inference significantly reduces detection accuracy.Based on this weakness, we propose Temp-Paraphraser, a simple yet effective paraphrasing framework that simulates high-temperature sampling effects through multiple normaltemperature generations, effectively evading detection.Experiments show that TempParaphraser reduces detector accuracy by an average of 82.5% while preserving high text quality.We also demonstrate that training on TempParaphraser-augmented data improves detector robustness.

Misinformation spans various domains, but detection methods trained on specific domains often perform poorly when applied to others.With the rapid development of Large Language Models (LLMs), researchers have begun to utilize LLMs for cross-domain misinformation detection.However, existing LLM-based methods often fail to adequately analyze news in the target domain, limiting their detection capabilities.More importantly, these methods typically rely on manually designed decision rules, which are limited by domain knowledge and expert experience, thus limiting the generalizability of decision rules to different domains.To address these issues, we propose a Multi-Agent Framework for cross-domain misinformation detection with Automated Decision Rule Optimization (MARO).Under this framework, we first employs multiple expert agents to analyze target-domain news.Subsequently, we introduce a question-reflection mechanism that guides expert agents to facilitate higher-quality analysis.Furthermore, we propose a decision rule optimization approach based on carefully designed cross-domain validation tasks to iteratively enhance decision rule effectiveness across domains.Experimental results and analysis on commonly used datasets demonstrate that MARO achieves significant improvements over existing methods. Multi-Dimensional Analysis Module Decision Rule Validation ModuleWow, this sounds amazing ... .

The goal of open relation extraction (OpenRE) is to develop an RE model that can generalize to new relations not encountered during training. Existing studies primarily formulate OpenRE as a clustering task. They first cluster all test instances based on the similarity between the instances, and then manually assign a new relation to each cluster. However, their reliance on human annotation limits their practicality. In this paper, we propose an OpenRE framework based on large language models (LLMs), which directly predicts new relations for test instances by leveraging their strong language understanding and generation abilities, without human intervention. Specifically, our framework consists of two core components: (1) a relation discoverer (RD), designed to predict new relations for test instances based on demonstrations formed by training instances with known relations; and (2) a relation predictor (RP), used to select the most likely relation for a test instance from n candidate relations, guided by demonstrations composed of their instances. To enhance the ability of our framework to predict new relations, we design a self-correcting inference strategy composed of three stages: relation discovery, relation denoising, and relation prediction. In the first stage, we use RD to preliminarily predict new relations for all test instances. Next, we apply RP to select some high-reliability test instances for each new relation from the prediction results of RD through a cross-validation method. During the third stage, we employ RP to re-predict the relations of all test instances based on the demonstrations constructed from these reliable test instances. Extensive experiments on three OpenRE datasets demonstrate the effectiveness of our framework. We release our code at https://github.com/XMUDeepLIT/LLM-OREF.git.

Metaphor detection, a critical task in natural language processing, involves identifying whether a particular word in a sentence is used metaphorically. Traditional approaches often rely on supervised learning models that implicitly encode semantic relationships based on metaphor theories. However, these methods often suffer from a lack of transparency in their decision-making processes, which undermines the reliability of their predictions. Recent research indicates that LLMs (large language models) exhibit significant potential in metaphor detection. Nevertheless, their reasoning capabilities are constrained by predefined knowledge graphs. To overcome these limitations, we propose DMD, a novel dual-perspective framework that harnesses both implicit and explicit applications of metaphor theories to guide LLMs in metaphor detection and adopts a self-judgment mechanism to validate the responses from the aforementioned forms of guidance. In comparison to previous methods, our framework offers more transparent reasoning processes and delivers more reliable predictions. Experimental results prove the effectiveness of DMD, demonstrating state-of-the-art performance across widely-used datasets.

Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly when dealing with previously unseen named entities. To tackle this challenge, we propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs. Specifically, we first use a large language model (LLM) to generate sentences from the sampled named entities and then use a text-to-speech (TTS) system to generate the speech. Furthermore, we introduce a noise metric to filter out noisy data. To evaluate our approach, we release a novel Spoken NER benchmark along with a corresponding NED containing 8,853 entities. Experiment results show that our method achieves state-of-the-art (SOTA) performance in the in-domain, zero-shot domain adaptation, and fully zero-shot settings. Our data will be available at https://github.com/DeepLearnXMU/HeardU.

Existing methods for code generation use code snippets as seed data, restricting the complexity and diversity of the synthesized data. In this paper, we introduce a novel feature tree-based synthesis framework, which revolves around hierarchical code features derived from high-level abstractions of code. The feature tree is constructed from raw data and refined iteratively to increase the quantity and diversity of the extracted features, which captures and recognizes more complex patterns and relationships within the code. By adjusting the depth and breadth of the sampled subtrees, our framework provides precise control over the complexity of the generated code, enabling functionalities that range from function-level operations to multi-file scenarios. We fine-tuned widely-used base models to obtain EpiCoder series, achieving state-of-the-art performance on multiple benchmarks at both the function and file levels. In particular, empirical evidence indicates that our approach shows significant potential in the synthesizing of repository-level code data. Our code and data are publicly available.

Large Vision-Language Models (LVLMs) have experienced significant advancements in recent years. However, their performance still falls short in tasks requiring deep visual perception, such as identifying subtle differences between images. A potential cause is the scarcity of visual knowledge in popular instruction-tuning corpora, resulting in inadequate visual perception and reasoning capabilities. To address this challenge, we introduce a self-improvement framework grounded in a novel visual knowledge-intensive task, Causality-driven Visual object Completion (CVC). This task requires LVLMs to infer the masked object in an image based on its causal relationships with the other visible information. We first obtain rich examples cheaply through our automated instance construction pipeline, without relying on sophisticated LVLMs (e.g., GPT-4V) or human assistance. Then, LVLMs effectively self-improve through trial and error learning using these created instances. Our experiments demonstrate substantial gains across four challenging specialized tasks and four widely-used comprehensive benchmarks. Especially on specialized tasks, our method achieves an average improvement of 5.4% and 4.0% compared to the corresponding baselines when utilizing LLaVA-1.5-7B and LLaVA-1.5-13B, respectively. Code and the supplementary file are available at https://github.com/XMUDeepLIT/CVC.

The advancement of Large Language Models (LLMs) has brought substantial attention to the Chain of Thought (CoT) approach, primarily due to its ability to enhance the capability of LLMs on complex reasoning tasks. Moreover, the CoT approach extends to multi-modal tasks of LLMs. However, the selection of optimal CoT demonstration examples for LLMs in multi-modal reasoning remains less explored due to the inherent complexity of multi-modal examples. In this paper, we introduce a novel approach that addresses this challenge by using retrieval mechanisms to dynamically select demonstration examples based on cross-modal and intra-modal similarities. Furthermore, we employ a Group Selection method to select examples containing rationales from different retrieval directions to promote the diversity of demonstration examples. To the best of our knowledge, we are the first to apply Retrieval-Augmented Generation (RAG) with CoT to complex multi-modal reasoning tasks. Through a series of experiments on two popular benchmarks, ScienceQA and MathVista, we demonstrate that our approach significantly improves the performance of GPT-4 by 6% on ScienceQA and 12.9% on MathVista. Additionally, it enhances the performance of GPT-4V on these two datasets by 2.7%, respectively, further advancing the capabilities of the most advanced LLMs and Large Multimodal Models (LMMs) for complex multi-modal reasoning tasks.

The development of Large Language Models (LLMs) has revolutionized QA across various industries, including the database domain. However, there lacks a thorough evaluation regarding the capabilities of different LLMs in database QA. To this end, we introduce DQABench, the first comprehensive database QA benchmark for LLMs. DQABench features an innovative LLM-based method to automate the generation, cleaning, and rewriting of evaluation dataset, resulting in over 200,000 QA pairs in English and Chinese. These QA pairs cover a wide range of database-specific knowledge extracted from manuals, online communities, and DB instances, allowing for assessment of LLMs' Retrieval-Augmented Generation (RAG) and Tool Invocation Generation (TIG) capabilities in the database QA task. Furthermore, we propose a highly modular and scalable testbed DQATestbed, with basic and advanced components such as Fine-tuning, Question Classification Routing (QCR), RAG, TIG, and Prompt Template Engineering (PTE). Finally, we provide an evaluation pipeline that computes various metrics throughout a standardized evaluation process to ensure the accuracy and fairness. Our evaluation reveals the strengths and limitations of nine open-source and commercial LLMs, and the impact of various service components (e.g., fine-tuning, QCR, RAG, TIG). The proposed benchmark dataset is available at https://github.com/XMUDM/DQABench.

Recently, video editing task has gained widespread attention due to its practical applications and rapid advancements. However, current automatic evaluation metrics for video editing are mostly poorly aligned with human judgments. Thus, researchers heavily rely on human evaluation, which is not only labor-intensive but also difficult to ensure consistency and objectivity. To address these issues, we propose EditEval, the largest-ever video editing benchmark to comprehensively evaluate the performance of video editing models in three aspects: Textual Faithfulness, Frame Consistency, and Video Fidelity. It includes 200 video clips and 1,010 text prompts, from which 160 instances are sampled to generate 1,280 edited videos using eight open-source video editing models, accompanied by human annotations. Furthermore, we propose EditScore, leveraging the advanced reasoning and comprehension capabilities of Multi-modal Large Language Models (MLLMs) as evaluators to assess edited videos across the aforementioned aspects. Experiments show that the best-performing video editing model only reaches an average score of 3.16 (out of a perfect 5), highlighting the challenge of EditEval. Besides, results from more than 10 MLLMs demonstrate the great potential of utilizing EditScore for automatic evaluation. Notably, for textual faithfulness, EditScore equipped with LLaVA-OneVision-7B achieves a significantly higher Pearson Correlation score compared to previous methods based on CLIP (0.50 vs 0.22). The code and dataset are available at: https://github.com/XMUDeepLIT/EditEval

While non-autoregressive sign language translation (NASLT) has the advantage in inference speed, the translation quality of NASLT models lags significantly behind that of the state-of-the-art (SOTA) autoregressive sign language translation (ASLT) models. To bridge the quality gap, we exploit glosses to unlock the potential of NASLT models. Concretely, we propose Gloss-enhanced Levenshtein Transformer (GLevT) for sign language translation (SLT), which takes glosses as initial sequences for editing into texts. In particular, to alleviate the inconsistency between training and inference of GLevT, which is introduced by glosses, we propose a dual-centric learning policy and a keyframe-based gloss replacement method for training, further improving the translation quality of GLevT. Experiments on CSL-Daily demonstrate that GLevT outperforms other NASLT models by approximately 4 points in BLEU and ROUGE scores, while achieving performance comparable to the SOTA ASLT models with a 3.46~5.26× inference speed-up. Furthermore, we extend GLevT to gloss-free SLT, achieving performance comparable to SOTA large models, despite having only 49M parameters. We release code at https://github.com/XMUDeepLIT/GLevT.

Leveraging vast and continually updated knowledge from the Internet has been considered an important ability for a dialogue system. Therefore, the dialogue query generation task is proposed for generating search queries from dialogue histories, which will be submitted to a search engine for retrieving relevant websites on the Internet. In this regard, previous efforts were devoted to collecting conversations with annotated queries and training a query producer (QP) via standard supervised learning. However, these studies still face the challenges of data scarcity and domain adaptation. To address these issues, in this paper, we propose a semi-supervised learning framework -- SemiDQG, to improve model performance with unlabeled conversations. Based on the observation that the search query is typically related to the topic of dialogue response, we train a response-augmented query producer (RA) to provide rich and effective training signals for QP. We first apply a similarity-based query selection strategy to select high-quality RA-generated pseudo queries, which are used to construct pseudo instances for training QP and RA. Then, we adopt the REINFORCE algorithm to further enhance QP, with RA-provided rewards as fine-grained training signals. Experimental results and in-depth analysis of three benchmarks show the effectiveness of our framework in cross-domain and low-resource scenarios. Particularly, SemiDQG significantly surpasses ChatGPT and competitive baselines. Our code is available at \url{https://github.com/DeepLearnXMU/SemiDQG}.

Sign language translation (SLT) aims to convert continuous sign language videos into textual sentences. As a typical multi-modal task, there exists an inherent modality gap between sign language videos and spoken language text, which makes the cross-modal alignment between visual and textual modalities crucial. However, previous studies tend to rely on an intermediate sign gloss representation to help alleviate the cross-modal problem thereby neglecting the alignment across modalities that may lead to compromised results. To address this issue, we propose a novel framework based on Conditional Variational autoencoder for SLT (CV-SLT) that facilitates direct and sufficient cross-modal alignment between sign language videos and spoken language text. Specifically, our CV-SLT consists of two paths with two Kullback-Leibler (KL) divergences to regularize the outputs of the encoder and decoder, respectively. In the prior path, the model solely relies on visual information to predict the target text; whereas in the posterior path, it simultaneously encodes visual information and textual knowledge to reconstruct the target text. The first KL divergence optimizes the conditional variational autoencoder and regularizes the encoder outputs, while the second KL divergence performs a self-distillation from the posterior path to the prior path, ensuring the consistency of decoder outputs.We further enhance the integration of textual information to the posterior path by employing a shared Attention Residual Gaussian Distribution (ARGD), which considers the textual information in the posterior path as a residual component relative to the prior path. Extensive experiments conducted on public datasets demonstrate the effectiveness of our framework, achieving new state-of-the-art results while significantly alleviating the cross-modal representation discrepancy. The code and models are available at https://github.com/rzhao-zhsq/CV-SLT.

Zhiwei Cao, Qian Cao, Yu Lu, Ningxin Peng, Luyang Huang, Shanbo Cheng, Jinsong Su. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Jianheng Huang, Leyang Cui, Ante Wang, Chengyi Yang, Xinting Liao, Linfeng Song, Junfeng Yao, Jinsong Su. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

The field of bioinformatics has seen significant progress, making the cross-modal text-molecule retrieval task increasingly vital. This task focuses on accurately retrieving molecule structures based on textual descriptions, by effectively aligning textual descriptions and molecules to assist researchers in identifying suitable molecular candidates. However, many existing approaches overlook the details inherent in molecule substructures. In this work, we introduce the Optimal Transport-based Multi-grained Alignments model (ORMA), a novel approach that facilitates multi-grained alignments between textual descriptions and molecules. Our model features a text encoder and a molecule encoder. The text encoder processes textual descriptions to generate both token-level and sentence-level representations, while molecules are modeled as hierarchical heterogeneous graphs, encompassing atom, motif, and molecule nodes to extract representations at these three levels. A key innovation in ORMA is the application of Optimal Transport (OT) to align tokens with motifs, creating multi-token representations that integrate multiple token alignments with their corresponding motifs. Additionally, we employ contrastive learning to refine cross-modal alignments at three distinct scales: token-atom, multitoken-motif, and sentence-molecule, ensuring that the similarities between correctly matched text-molecule pairs are maximized while those of unmatched pairs are minimized. To our knowledge, this is the first attempt to explore alignments at both the motif and multi-token levels. Experimental results on the ChEBI-20 and PCdes datasets demonstrate that ORMA significantly outperforms existing state-of-the-art (SOTA) models. Specifically, in text-molecule retrieval on ChEBI-20, our model achieves a Hits@1 score of 66.5%, surpassing the SOTA model AMAN by 17.1%. Similarly, in molecule-text retrieval, ORMA secures a Hits@1 score of 61.6%, outperforming AMAN by 15.0%.

Cross-modal text-molecule retrieval model aims to learn a shared feature space of the text and molecule modalities for accurate similarity calculation, which facilitates the rapid screening of molecules with specific properties and activities in drug design. However, previous works have two main defects. First, they are inadequate in capturing modality-shared features considering the significant gap between text sequences and molecule graphs. Second, they mainly rely on contrastive learning and adversarial training for cross-modality alignment, both of which mainly focus on the first-order similarity, ignoring the second-order similarity that can capture more structural information in the embedding space. To address these issues, we propose a novel cross-modal text-molecule retrieval model with two-fold improvements. Specifically, on the top of two modality-specific encoders, we stack a memory bank based feature projector that contain learnable memory vectors to extract modality-shared features better. More importantly, during the model training, we calculate four kinds of similarity distributions (text-to-text, text-to-molecule, molecule-to-molecule, and molecule-to-text similarity distributions) for each instance, and then minimize the distance between these similarity distributions (namely second-order similarity losses) to enhance cross-modal alignment. Experimental results and analysis strongly demonstrate the effectiveness of our model. Particularly, our model achieves SOTA performance, outperforming the previously-reported best result by 6.4%.

In an emotional conversation, emotions are causally transmitted among communication participants, constituting a fundamental conversational feature that can facilitate the comprehension of intricate changes in emotional states during the conversation and contribute to neutralizing emotional semantic bias in utterance caused by the absence of modality information. Therefore, emotional transition (ET) plays a crucial role in the task of Emotion Recognition in Conversation (ERC) that has not received sufficient attention in current research. In light of this, an Emotional Transition-based Emotion Recognizer (EmoTrans) is proposed in this paper. Specifically, we concatenate the most recent utterances with their corresponding speakers to construct the model input, known as samples, each with several placeholders to implicitly express the emotions of contextual utterances. Based on these placeholders, two components are developed to make the model sensitive to emotions and effectively capture the ET features in the sample. Furthermore, an ET-based Contrastive Learning (CL) is developed to compact the representation space, making the model achieve more robust sample representations. We conducted exhaustive experiments on four widely used datasets and obtained competitive experimental results, especially, new state-of-the-art results obtained on MELD and IEMOCAP, demonstrating the superiority of EmoTrans.

Electronic health records (EHRs) serve as a digital repository storing comprehensive medical information about patients. Representation learning for EHRs plays a crucial role in healthcare applications. In this paper, we propose a Multimodal Heterogeneous Graph-enhanced Representation Learning, denoted as MHGRL, aimed at learning effective EHR representations. To address the challenge posed by data insufficiency of EHRs, MHGRL utilizes a multimodal heterogeneous graph to model an EHR. Specifically, we construct a heterogeneous graph for each EHR and enrich it by incorporating multimodal information with medical ontology and textual notes. With the integration of pre-trained model, graph neural network, and attention mechanism, MHGRL effectively incorporates both node attributes and structural information across a multimodal heterogeneous graph. Moreover, we employ contrastive learning to ensure the consistency of representations for similar EHRs and improve the model robustness. The experimental results show that MHGRL outperforms all baselines on two real clinical datasets in downstream tasks, including EHR clustering and disease prediction. The code is available at https://github.com/emmali808/MHGRL.

Traditional non-simultaneous Sign Language Translation (SLT) methods, while effective for pre-recorded videos, face challenges in real-time scenarios due to inherent inference delays. The emerging field of simultaneous SLT aims to address this issue by progressively translating incrementally received sign video. However, the sole existing work in simultaneous SLT adopts a fixed gloss-based policy, which suffer from limitations in boundary prediction and contextual comprehension. In this paper, we delve deeper into this area and propose an adaptive policy for simultaneous SLT. Our approach introduces the concept of “confident translation length”, denoting maximum accurate translation achievable from current input. An estimator measures this length for streaming sign video, enabling the model to make informed decisions on whether to wait for more input or proceed with translation. To train the estimator, we construct a training data of confident translation length based on the longest common prefix between translations of partial and complete inputs. Furthermore, we incorporate adaptive training, utilizing pseudo prefix pairs, to refine the offline translation model for optimal performance in simultaneous scenarios. Experimental results on PHOENIX2014T and CSL-Daily demonstrate the superiority of our adaptive policy over existing methods, particularly excelling in situations requiring extremely low latency.

One challenge in text-to-image (T2I) generation is the inadvertent reflection of culture gaps present in the training data, which signifies the disparity in generated image quality when the cultural elements of the input text are rarely collected in the training set. Although various T2I models have shown impressive but arbitrary examples, there is no benchmark to systematically evaluate a T2I model’s ability to generate cross-cultural images. To bridge the gap, we propose a Challenging Cross-Cultural (C3) benchmark with comprehensive evaluation criteria, which can assess how well-suited a model is to a target culture. By analyzing the flawed images generated by the Stable Diffusion model on the C3 benchmark, we find that the model often fails to generate certain cultural objects. Accordingly, we propose a novel multi-modal metric that considers object-text alignment to filter the fine-tuning data in the target culture, which is used to fine-tune a T2I model to improve cross-cultural generation. Experimental results show that our multi-modal metric provides stronger data selection performance on the C3 benchmark than existing metrics, in which the object-text alignment is crucial. We release the benchmark, data, code, and generated images to facilitate future research on culturally diverse T2I generation.

Gesture recognition based on surface electromyography (sEMG) has seen considerable improvements in performance across various tasks and metrics with the rapid development of deep learning. However, challenges still exist in current deep neural networks for sEMG recognition. For instance, convolutional neural networks exhibit poor capturing of global features, recurrent neural networks have limited parallel processing capabilities, and their hybrids are usually more complex. Additionally, recent networks based on Transformers rarely consider the locality of attention and noise resistance. To fully explore the essence of sEMG sequences, and to make the model more lightweight and robust while ensuring feature learning performance, in this paper, we propose the feature distilled variational information bottleneck (FDVIB). Specifically, this method leverages knowledge distillation to learn from a high-precision teacher model at levels of feature and prediction, significantly reducing parameters and computations, and simplifying the structure. It also uses VIB to enhance the model’s robustness. We construct a Transformer model using the proposed method and conduct a series of evaluations. Experimental results show that our classification accuracy is competitive with state-of-the-art and also demonstrate the effectiveness of our method in enhancing model lightness and robustness.

Diffusion-based text-to-image models have demonstrated impressive achievements in diversity and aesthetics but struggle to generate images with legible visual texts. Existing backbone models have limitations such as misspelling, failing to generate texts, and lack of support for Chinese texts, but their development shows promising potential. In this paper, we propose a series of methods, aiming to empower backbone models to generate visual texts in English and Chinese. We first conduct a preliminary study revealing that BPE tokenization and insufficient learning of cross-attention modules restrict the performance of the backbone models. Based on these observations, we make the following improvements: (1) We design a mixed granularity input strategy to provide more suitable text representations; (2) We propose to augment the conventional training objective with three glyph-aware training losses, which enhance the learning of cross-attention modules and encourage the model to focus on visual texts. Through experiments, we demonstrate that our methods can effectively empower backbone models to generate semantic relevant, aesthetically appealing, and accurate visual text images, while maintaining their fundamental image generation quality.

Keyphrase generation (KPG) aims to automatically generate a collection of phrases representing the core concepts of a given document.The dominant paradigms in KPG include ONE2SEQ and ONE2SET.Recently, there has been increasing interest in applying large language models (LLMs) to KPG.Our preliminary experiments reveal that it is challenging for a single model to excel in both recall and precision.Further analysis shows that: 1) the ONE2SET paradigm owns the advantage of high recall, but suffers from improper assignments of supervision signals during training; 2) LLMs are powerful in keyphrase selection, but existing selection methods often make redundant selections.Given these observations, we introduce a generate-then-select framework decomposing KPG into two steps, where we adopt a ONE2SET-based model as generator to produce candidates and then use an LLM as selector to select keyphrases from these candidates.Particularly, we make two important improvements on our generator and selector: 1) we design an Optimal Transport-based assignment strategy to address the above improper assignments; 2) we model the keyphrase selection as a sequence labeling task to alleviate redundant selections.Experimental results on multiple benchmark datasets show that our framework significantly surpasses state-of-theart models, especially in absent keyphrase prediction.We release our code at https:// github.

Due to the continuous emergence of new data, version updates have become an indispensable requirement for Large Language Models (LLMs).The training paradigms for version updates of LLMs include pre-training from scratch (PTFS) and continual pre-training (CPT).Preliminary experiments demonstrate that PTFS achieves better pre-training performance, while CPT has lower training cost.Moreover, their performance and training cost gaps widen progressively with version updates.To investigate the underlying reasons for this phenomenon, we analyze the effect of learning rate adjustments during the two stages of CPT: preparing an initialization checkpoint and continual pre-training based on this checkpoint.We find that a large learning rate in the first stage and a complete learning rate decay process in the second stage are crucial for version updates of LLMs.Hence, we propose a learning rate path switching training paradigm.Our paradigm comprises one main path, where we pre-train a LLM with the maximal learning rate, and multiple branching paths, each of which corresponds to an update of the LLM with newly-added training data.Extensive experiments demonstrate the effectiveness and generalization of our paradigm.Particularly, when training four versions of LLMs, our paradigm reduces the total training cost to 58% compared to PTFS, while maintaining comparable pretraining performance.

Liang Zhang, Zhen Yang, Biao Fu, Ziyao Lu, Liangying Shao, Shiyu Liu, Fandong Meng, Jie Zhou, Xiaoli Wang, Jinsong Su. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Multi-modal Recommendation Systems (MRSs) utilize diverse modalities, such as image and text, to enrich item representations and enhance recommendation accuracy. Current MRSs overlook the large misalignment between multi-modal content features and ID embeddings. While bidirectional alignment between visual and textual modalities has been extensively studied in large multi-modal models, this study suggests that multi-modal alignment in MRSs should be in a one-way direction. A plug-and-play framework is presented, called FEedback-orienTed mulTi-modal aLignmEnt (FETTLE). FETTLE contains three novel solutions: (1) it automatically determines item-level alignment direction between each pair of modalities based on estimated user feedback; (2) it coordinates the alignment directions among multiple modalities; (3) it implements cluster-level alignment from both user and item perspectives for more stable alignments. Extensive experiments on three real datasets demonstrate that FETTLE significantly improves various backbone models. Conventional collaborative filtering models are improved by 24.79%-62.79%, and recent MRSs are improved by 5.91% - 20.11%.

Molecular representation learning is a fundamental problem in the field of drug discovery and molecular science. Whereas incorporating molecular 3D information in the representations of molecule seems beneficial, which is related to computational chemistry with the basic task of predicting stable 3D structures (conformations) of molecules. Existing machine learning methods either rely on 1D and 2D molecular properties or simulate molecular force field to use additional 3D structure information via Hamiltonian network. The former has the disadvantage of ignoring important 3D structure features, while the latter has the disadvantage that existing Hamiltonian neural network must satisfy the “canonial” constraint, which is difficult to be obeyed in many cases. In this paper, we propose a novel plug-and-play architecture LagNet by simulating molecular force field only with parameterized position coordinates, which implements Lagrangian mechanics to learn molecular representation by preserving 3D conformation without obeying any additional restrictions. LagNet is designed to generate known conformations and generalize for unknown ones from molecular SMILES. Implicit positions in LagNet are learned iteratively using discrete-time Lagrangian equations. Experimental results show that LagNet can well learn 3D molecular structure features, and outperforms previous state-of-the-art baselines related molecular representation by a significant margin.

Hyperparameter tuning is an essential task in automatic machine learning and big data management. To accelerate tuning, many recent studies focus on augmenting BO, the primary hyperparameter tuning strategy, by transferring information from other tuning tasks. However, existing studies ignore program similarities in their transfer mechanism, thus they are sub-optimal in cross-program transfer when tuning tasks involve different programs. This paper proposes CaTHPO, a code-aware cross-program transfer hyperparameter optimization framework, which makes three improvements. (1) It learns code-aware program representation in a self-supervised manner to give an off-the-shelf estimate of program similarities. (2) It adjusts the surrogate and AF in BO based on program similarities, thus the hyperparameter search is guided by accumulated information across similar programs. (3) It presents a safe controller to dynamically prune undesirable sample points based on tuning experiences of similar programs. Extensive experiments on tuning various recommendation models and Spark applications have demonstrated that CatHPO can steadily obtain better and more robust hyperparameter performances within fewer samples than state-of-the-art competitors.

Document-level relation extraction (RE) aims to extract relational triples from a document. One of its primary challenges is to predict implicit relations between entities, which are not explicitly expressed in the document but can usually be extracted through relational reasoning. Previous methods mainly implicitly model relational reasoning through the interaction among entities or entity pairs. However, they suffer from two deficiencies: 1) they often consider only one reasoning pattern, of which coverage on relational triples is limited; 2) they do not explicitly model the process of relational reasoning. In this paper, to deal with the first problem, we propose a document-level RE model with a reasoning module that contains a core unit, the reasoning multi-head self-attention unit. This unit is a variant of the conventional multi-head self-attention and utilizes four attention heads to model four common reasoning patterns, respectively, which can cover more relational triples than previous methods. Then, to address the second issue, we propose a self-distillation training framework, which contains two branches sharing parameters. In the first branch, we first randomly mask some entity pair feature vectors in the document, and then train our reasoning module to infer their relations by exploiting the feature information of other related entity pairs. By doing so, we can explicitly model the process of relational reasoning. However, because the additional masking operation is not used during testing, it causes an input gap between training and testing scenarios, which would hurt the model performance. To reduce this gap, we perform conventional supervised training without masking operation in the second branch and utilize Kullback-Leibler divergence loss to minimize the difference between the predictions of the two branches. Finally, we conduct comprehensive experiments on three benchmark datasets, of which experimental results demonstrate that our model consistently outperforms all competitive baselines. Our source code is available at https://github.com/DeepLearnXMU/DocRE-SD

Zhiwei Cao, Baosong Yang, Huan Lin, Suhang Wu, Xiangpeng Wei, Dayiheng Liu, Jun Xie, Min Zhang, Jinsong Su. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Zhibin Lan, Jiawei Yu, Xiang Li, Wen Zhang, Jian Luan, Bin Wang, Degen Huang, Jinsong Su. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

A persistent goal of multilingual neural machine translation (MNMT) is to continually adapt the model to support new language pairs or improve some current language pairs without accessing the previous training data.To achieve this, the existing methods primarily focus on preventing catastrophic forgetting by making compromises between the original and new language pairs, leading to sub-optimal performance on both translation tasks.To mitigate this problem, we propose a dual importancebased model division method to divide the model parameters into two parts and separately model the translation of the original and new tasks.Specifically, we first remove the parameters that are negligible to the original tasks but essential to the new tasks to obtain a pruned model, which is responsible for the original translation tasks.Then we expand the pruned model with external parameters and fine-tune the newly added parameters with new training data.The whole fine-tuned model will be used for the new translation tasks.Experimental results show that our method can efficiently adapt the original model to various new translation tasks while retaining the performance of the original tasks.Further analyses demonstrate that our method consistently outperforms several strong baselines under different incremental translation scenarios.

Conventional knowledge distillation (KD) approaches are commonly employed to compress neural machine translation (NMT) models.However, they only obtain one lightweight student each time.Consequently, we have to conduct KD multiple times when different students are required at the same time, which could be resource-intensive.Additionally, these students are individually optimized, and thus lack interactions with each other, leading to their potential not being fully exerted.In this work, we propose a novel All-In-One Knowledge Distillation (AIO-KD) framework for NMT, which generates multiple satisfactory students at once.Under AIO-KD, we first randomly extract fewer-layer subnetworks from the teacher as the sample students.Then, we jointly optimize the teacher and these students, where the students simultaneously learn the knowledge from the teacher and interact with other students via mutual learning.When utilized, we re-extract the candidate students, satisfying the specifications of various devices.Particularly, we adopt carefully-designed strategies for AIO-KD: 1) we dynamically detach gradients to prevent poorly-performed students from negatively affecting the teacher during the knowledge transfer, which could subsequently impact other students; 2) we design a twostage mutual learning strategy, which alleviates the negative impacts of poorly-performed students on the early-stage student interactions.Extensive experiments and in-depth analyses on three benchmarks demonstrate the effectiveness and eco-friendliness of AIO-KD.Our source code is available at https://github. com/DeepLearnXMU/AIO-KD.

As commonly-used methods for debiasing natural language understanding (NLU) models, dataset refinement approaches heavily rely on manual data analysis, and thus maybe unable to cover all the potential biased features.In this paper, we propose IBADR, an Iterative Bias-Aware Dataset Refinement framework, which debiases NLU models without predefining biased features.We maintain an iteratively expanded sample pool.Specifically, at each iteration, we first train a shallow model to quantify the bias degree of samples in the pool.Then, we pair each sample with a bias indicator representing its bias degree, and use these extended samples to train a sample generator.In this way, this generator can effectively learn the correspondence relationship between bias indicators and samples.Furthermore, we employ the generator to produce pseudo samples with fewer biased features by feeding specific bias indicators.Finally, we incorporate the generated pseudo samples into the pool.Experimental results and in-depth analyses on two NLU tasks show that IBADR not only significantly outperforms existing dataset refinement approaches, achieving SOTA, but also is compatible with model-centric methods. 1

Few-shot relation extraction (FSRE) aims to train a model that can deal with new relations using only a few labeled examples.Most existing studies employ Prototypical Networks for FSRE, which usually overfits the relation classes in the training set and cannot generalize well to unseen relations.By investigating the class separation of an FSRE model, we find that model upper layers are prone to learn relation-specific knowledge.Therefore, in this paper, we propose a HyperNetworkbased Decoupling approach to improve the generalization of FSRE models.Specifically, our model consists of an encoder, a network generator (for producing relation classifiers) and the generated-then-finetuned classifiers for every N -way-K-shot episode.Meanwhile, we design a two-step training strategy along with a class-agnostic aligner, by which the generated classifiers focus on acquiring relation-specific knowledge and the encoder is encouraged to learn more general relation knowledge.In this way, the roles of upper and lower layers in our FSRE model are explicitly decoupled, thus enhancing its generalizing capability during testing.Experiments on two public datasets demonstrate the effectiveness of our method.Our source code is available at https: //github.com/DeepLearnXMU/FSRE-HDN.

In document-level relation extraction (RE), the models are required to correctly predict implicit relations in documents via relational reasoning. To this end, many graph-based methods have been proposed for this task. Despite their success, these methods still suffer from several drawbacks: 1) their interaction between document encoder and graph encoder is usually unidirectional and insufficient; 2) their graph encoders often fail to capture the global context of nodes in document graph. In this paper, we propose a document-level RE model with a Graph-Transformer Network (GTN). The GTN includes two core sublayers: 1) the graph-attention sublayer that simultaneously models global and local contexts of nodes in the document graph; 2) the cross-attention sublayer, enabling GTN to capture the non-entity clue information from the document encoder. Furthermore, we introduce two auxiliary training tasks to enhance the bidirectional semantic interaction between the document encoder and GTN: 1) the graph node reconstruction that can effectively train our cross-attention sublayer to enhance the semantic transition from the document encoder to GTN; 2) the structure-aware adversarial knowledge distillation, by which we can effectively transfer the structural information of GTN to the document encoder. Experimental results on four benchmark datasets prove the effectiveness of our model. Our source code is available at https://github.com/DeepLearnXMU/DocRE-BSI.

Multi-modal keyphrase generation aims to produce a set of keyphrases that represent the core points of the input text-image pair. In this regard, dominant methods mainly focus on multi-modal fusion for keyphrase generation. Nevertheless, there are still two main drawbacks: 1) only a limited number of sources, such as image captions, can be utilized to provide auxiliary information. However, they may not be sufficient for the subsequent keyphrase generation. 2) the input text and image are often not perfectly matched, and thus the image may introduce noise into the model. To address these limitations, in this paper, we propose a novel multi-modal keyphrase generation model, which not only enriches the model input with external knowledge, but also effectively filters image noise. First, we introduce external visual entities of the image as the supplementary input to the model, which benefits the cross-modal semantic alignment for keyphrase generation. Second, we simultaneously calculate an image-text matching score and image region-text correlation scores to perform multi-granularity image noise filtering. Particularly, we introduce the correlation scores between image regions and ground-truth keyphrases to refine the calculation of the previously-mentioned correlation scores. To demonstrate the effectiveness of our model, we conduct several groups of experiments on the benchmark dataset. Experimental results and in-depth analyses show that our model achieves the state-of-the-art performance. Our code is available on https://github.com/DeepLearnXMU/MM-MKP.

Conditional text generation is supposed to generate a fluent and coherent target text that is faithful to the source text. Although pre-trained models have achieved promising results, they still suffer from the crucial factuality problem. To deal with this issue, we propose a factuality-aware pretraining-finetuning framework named FactGen, which fully considers factuality during two training stages. Specifically, at the pre-training stage, we utilize a natural language inference model to construct target texts that are entailed by the source texts, resulting in a more factually consistent pre-training objective. Then, during the fine-tuning stage, we further introduce a contrastive ranking loss to encourage the model to generate factually consistent text with higher probability. Extensive experiments on three conditional text generation tasks demonstrate the effectiveness and generality of our training framework.

Neural chat translation (NCT) aims to translate a cross-lingual chat between speakers of different languages. Existing context-aware NMT models cannot achieve satisfactory performances due to the following inherent problems: 1) limited resources of annotated bilingual dialogues; 2) the neglect of modelling conversational properties; 3) training discrepancy between different stages. To address these issues, in this paper, we propose a multi-task multi-stage transitional (MMT) training framework, where an NCT model is trained using the bilingual chat translation dataset and additional monolingual dialogues. We elaborately design two auxiliary tasks, namely utterance discrimination and speaker discrimination, to introduce the modelling of dialogue coherence and speaker characteristic into the NCT model. The training process consists of three stages: 1) sentence-level pre-training on large-scale parallel corpus; 2) intermediate training with auxiliary tasks using additional monolingual dialogues; 3) context-aware fine-tuning with gradual transition. Particularly, the second stage serves as an intermediate phase that alleviates the training discrepancy between the pre-training and fine-tuning stages. Moreover, to make the stage transition smoother, we train the NCT model using a gradual transition strategy, i.e., gradually transiting from using monolingual to bilingual dialogues. Extensive experiments on two language pairs demonstrate the effectiveness and superiority of our proposed training framework.

Abstract We focus on the factuality property during the extraction of an OpenIE corpus named OpenFact, which contains more than 12 million high-quality knowledge triplets. We break down the factuality property into two important aspects—expressiveness and groundedness—and we propose a comprehensive framework to handle both aspects. To enhance expressiveness, we formulate each knowledge piece in OpenFact based on a semantic frame. We also design templates, extra constraints, and adopt human efforts so that most OpenFact triplets contain enough details. For groundedness, we require the main arguments of each triplet to contain linked Wikidata1 entities. A human evaluation suggests that the OpenFact triplets are much more accurate and contain denser information compared to OPIEC-Linked (Gashteovski et al., 2019), one recent high-quality OpenIE corpus grounded to Wikidata. Further experiments on knowledge base completion and knowledge base question answering show the effectiveness of OpenFact over OPIEC-Linked as supplementary knowledge to Wikidata as the major KG.

Controllable text generation is an appealing but challenging task, which allows users to specify particular attributes of the generated outputs. In this paper, we propose a controllable dialogue generation model to steer response generation under multi-attribute constraints. Specifically, we define and categorize the commonly-used control attributes into global and local ones, which possess different granularities of effects on response generation. Then, we significantly extend the conventional seq2seq framework by introducing a novel two-stage decoder, which first uses amulti-grainedstyle specification layerto impose the stylistic constraints and determine word-level control states of responses based on the attributes, and then employs aresponse generation layerto generate final responses maintaining both semantic relevancy to the contexts and fidelity to the attributes. Furthermore, we train our model with an attribute consistency reward to promote response control with explicit supervision signals. Extensive experiments and in-depth analyses on two datasets indicate that our model can significantly outperform competitive baselines in terms of response quality, content diversity and controllability.

Conversational discourse analysis aims to extract the interactions between dialogue turns, which is crucial for modeling complex multi-party dialogues. As the benchmarks are still limited in size and human annotations are costly, the current standard approaches apply pretrained language models, but they still require randomly initialized classifiers to make predictions. These classifiers usually require massive data to work smoothly with the pretrained encoder, causing severe data hunger issue. We propose two convenient strategies to formulate this task as a sequence generation problem, where classifier decisions are carefully converted into sequence of tokens. We then adopt a pretrained T5 1 model to solve this task so that no parameters are randomly initialized. We also leverage the descriptions of the discourse relations to help model understand their meanings. Experiments on two popular benchmarks show that our approach outperforms previous state-of-the-art models by a large margin, and it is also more robust in zero-shot and few-shot settings.

Referring expression comprehension (REC) is an emerging research topic in computer vision, which refers to the detection of a target region in an image given a test description. Most existing REC methods follow a multistage pipeline, which is computationally expensive and greatly limits the applications of REC. In this article, we propose a one-stage model toward real-time REC, termed real-time global inference network (RealGIN). RealGIN addresses the issues of expression diversity and complexity of REC with two innovative designs: adaptive feature selection (AFS) and Global Attentive ReAsoNing (GARAN). Expression diversity concerns varying expression content, which includes information such as colors, attributes, locations, and fine-grained categories. To address this issue, AFS adaptively fuses features of different semantic levels to tackle the changes in expression content. In contrast, expression complexity concerns the complex relational conditions in expressions that are used to identify the referent. To this end, GARAN uses the textual feature as a pivot to collect expression-aware visual information from all regions and then diffuses this information back to each region, which provides sufficient context for modeling the relational conditions in expressions. On five benchmark datasets, i.e., RefCOCO, RefCOCO+, RefCOCOg, ReferIT, and Flickr30k, the proposed RealGIN outperforms most existing methods and achieves very competitive performances against the most advanced one, i.e., MAttNet. More importantly, under the same hardware, RealGIN can boost the processing speed by 10-20 times over the existing methods.

Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. However, existing models cannot perform as well as humans, since sentences they produce are often implausible and grammatically incorrect. In this paper, inspired by the process of humans creating sentences, we propose a novel Knowledge-enhanced Commonsense Generation framework, termed KGR4, consisting of four stages: Retrieval, Retrospect, Refine, Rethink. Under this framework, we first perform retrieval to search for relevant sentences from external corpus as the prototypes. Then, we train the generator that either edits or copies these prototypes to generate candidate sentences, of which potential errors will be fixed by an autoencoder-based refiner. Finally, we select the output sentence from candidate sentences produced by generators with different hyper-parameters. Experimental results and in-depth analysis on the CommonGen benchmark strongly demonstrate the effectiveness of our framework. Particularly, KGR4 obtains 33.56 SPICE in the official leaderboard, outperforming the previously-reported best result by 2.49 SPICE and achieving state-of-the-art performance. We release the code at https://github.com/DeepLearnXMU/KGR-4.

Implicit discourse relation recognition (IDRR) is a challenging but crucial task in discourse analysis. Most existing methods train multiple models to predict multi-level labels independently, while ignoring the dependence between hierarchically structured labels. In this paper, we consider multi-level IDRR as a conditional label sequence generation task and propose a Label Dependence-aware Sequence Generation Model (LDSGM) for it. Specifically, we first design a label attentive encoder to learn the global representation of an input instance and its level-specific contexts, where the label dependence is integrated to obtain better label embeddings. Then, we employ a label sequence decoder to output the predicted labels in a top-down manner, where the predicted higher-level labels are directly used to guide the label prediction at the current level. We further develop a mutual learning enhanced training method to exploit the label dependence in a bottom-up direction, which is captured by an auxiliary decoder introduced during training. Experimental results on the PDTB dataset show that our model achieves the state-of-the-art performance on multi-level IDRR. We release our code at https://github.com/nlpersECJTU/LDSGM.

Yunlong Liang, Fandong Meng, Chulun Zhou, Jinan Xu, Yufeng Chen, Jinsong Su, Jie Zhou. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Most dominant neural machine translation (NMT) models are restricted to make predictions only according to the local context of preceding words in a left-to-right manner.Although many previous studies try to incorporate global information into NMT models, there still exist limitations on how to effectively exploit bidirectional global context.In this paper, we propose a Confidence Based Bidirectional Global Context Aware (CB-BGCA) training framework for NMT, where the NMT model is jointly trained with an auxiliary conditional masked language model (CMLM).The training consists of two stages:(1) multi-task joint training; (2) confidence based knowledge distillation.At the first stage, by sharing encoder parameters, the NMT model is additionally supervised by the signal from the CMLM decoder that contains bidirectional global contexts.Moreover, at the second stage, using the CMLM as teacher, we further pertinently incorporate bidirectional global context to the NMT model on its unconfidently-predicted target words via knowledge distillation.Experimental results show that our proposed CB-BGCA training framework significantly improves the NMT model by +1.02, +1.30 and +0.57BLEU scores on three large-scale translation datasets, namely WMT'14 Englishto-German, WMT'19 Chinese-to-English and WMT'14 English-to-French, respectively.

Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples. They require the model to translate both the authentic source sentence and its adversarial counterpart into the identical target sentence within the same training stage, which may be a suboptimal choice to achieve robust NMT. In this paper, we first conduct a preliminary study to confirm this claim and further propose an Iterative Scheduled Data-switch Training Framework to mitigate this problem. Specifically, we introduce two training stages, iteratively switching between authentic and adversarial examples. Compared with previous studies, our model focuses more on just one type of examples at each single stage, which can better exploit authentic and adversarial examples, and thus obtaining a better robust NMT model. Moreover, we introduce an improved curriculum learning method with a sampling strategy to better schedule the process of noise injection. Experimental results show that our model significantly surpasses several competitive baselines on four translation benchmarks. Our source code is available at https://github.com/DeepLearnXMU/RobustNMT-ISDST.

Most existing pre-trained language representation models (PLMs) are sub-optimal in sentiment analysis tasks, as they capture the sentiment information from word-level while underconsidering sentence-level information.In this paper, we propose SentiWSP, a novel Sentiment-aware pre-trained language model with combined Word-level and Sentence-level Pre-training tasks.The word level pre-training task detects replaced sentiment words, via a generator-discriminator framework, to enhance the PLM's knowledge about sentiment words.The sentence level pre-training task further strengthens the discriminator via a contrastive learning framework, with similar sentences as negative samples, to encode sentiments in a sentence.Extensive experimental results show that SentiWSP achieves new state-of-the-art performance on various sentence-level and aspectlevel sentiment classification benchmarks.We have made our code and model publicly available at https://github.com/XMUDM/SentiWSP.

k-Nearest-Neighbor Machine Translation (kNN-MT) becomes an important research direction of NMT in recent years.Its main idea is to retrieve useful key-value pairs from an additional datastore to modify translations without updating the NMT model.However, the underlying retrieved noisy pairs will dramatically deteriorate the model performance.In this paper, we conduct a preliminary study and find that this problem results from not fully exploiting the prediction of the NMT model.To alleviate the impact of noise, we propose a confidence-enhanced kNN-MT model with robust training.Concretely, we introduce the NMT confidence to refine the modeling of two important components of kNN-MT: kNN distribution and the interpolation weight.Meanwhile we inject two types of perturbations into the retrieved pairs for robust training.Experimental results on four benchmark datasets demonstrate that our model not only achieves significant improvements over current kNN-MT models, but also exhibits better robustness.Our code is available at https://github.com/ DeepLearnXMU/Robust-knn-mt.

Multilingual neural machine translation aims to translate multiple language pairs in a single model and has shown great success thanks to the knowledge transfer across languages with the shared parameters.Despite promising, this share-all paradigm suffers from insufficient ability to capture language-specific features.Currently, the common practice is to insert or search language-specific networks to balance the shared and specific features.However, those two types of features are not sufficient enough to model the complex commonality and divergence across languages, such as the locally shared features among similar languages, which leads to sub-optimal transfer, especially in massively multilingual translation.In this paper, we propose a novel token-level feature mixing method that enables the model to capture different features and dynamically determine the feature sharing across languages.Based on the observation that the tokens in the multilingual model are usually shared by different languages, we insert a feature mixing layer into each Transformer sublayer and model each token representation as a mix of different features, with a proportion indicating its feature preference.In this way, we can perform fine-grained feature sharing and achieve better multilingual transfer.Experimental results on multilingual datasets show that our method outperforms various strong baselines and can be extended to zero-shot translation.Further analyses reveal that our method can capture different linguistic features and bridge the representation gap across languages.

Keyphrase generation aims to automatically generate short phrases summarizing an input document.The recently emerged ONE2SET paradigm (Ye et al., 2021) generates keyphrases as a set and has achieved competitive performance.Nevertheless, we observe serious calibration errors outputted by ONE2SET, especially in the over-estimation of ∅ token (means "no corresponding keyphrase").In this paper, we deeply analyze this limitation and identify two main reasons behind: 1) the parallel generation has to introduce excessive ∅ as padding tokens into training instances; and 2) the training mechanism assigning target to each slot is unstable and further aggravates the ∅ token over-estimation.To make the model wellcalibrated, we propose WR-ONE2SET which extends ONE2SET with an adaptive instancelevel cost Weighting strategy and a target Reassignment mechanism.The former dynamically penalizes the over-estimated slots for different instances thus smoothing the uneven training distribution.The latter refines the original inappropriate assignment and reduces the supervisory signals of over-estimated slots.Experimental results on commonly-used datasets demonstrate the effectiveness and generality of our proposed paradigm.

Document-level relation extraction (RE) aimsto extract the relations between entities from the input document that usually containing many difficultly-predicted entity pairs whose relations can only be predicted through relational inference.Existing methods usually directly predict the relations of all entity pairs of input document in a one-pass manner, ignoring the fact that predictions of some entity pairs heavily depend on the predicted results of other pairs.To deal with this issue, in this paper, we propose a novel document-level RE model with iterative inference.Our model is mainly composed of two modules: 1) a base module expected to provide preliminary relation predictions on entity pairs; 2) an inference module introduced to refine these preliminary predictions by iteratively dealing with difficultlypredicted entity pairs depending on other pairs in an easy-to-hard manner.Unlike previous methods which only consider feature information of entity pairs, our inference module is equipped with two Extended Cross Attention units, allowing it to exploit both feature information and previous predictions of entity pairs during relational inference.Furthermore, we adopt a two-stage strategy to train our model.At the first stage, we only train our base module.During the second stage, we train the whole model, where contrastive learning is introduced to enhance the training of inference module.Experimental results on three commonly-used datasets show that our model consistently outperforms other competitive baselines.Our source code is available at https://github. com/DeepLearnXMU/DocRE-II.

Most existing recommendation models learn vectorized representations for items, i.e., item embeddings to make predictions. Item embeddings inherit popularity bias from the data, which leads to biased recommendations. We use this observation to design two simple and effective strategies, which can be flexibly plugged into different backbone recommendation models, to learn popularity neutral item representations. One strategy isolates popularity bias in one embedding direction and neutralizes the popularity direction post-training. The other strategy encourages all embedding directions to be disentangled and popularity neutral. We demonstrate that the proposed strategies outperform state-of-the-art debiasing methods on various real-world datasets, and improve recommendation quality of shallow and deep backbone models.

Dialogue understanding has always been a bottleneck for many conversational tasks, such as dialogue response generation and conversational question answering. To expedite the progress in this area, we introduce the task of conversational aspect sentiment analysis (CASA) that can provide useful fine-grained sentiment information for dialogue understanding and planning. Overall, this task extends the standard aspect-based sentiment analysis to the conversational scenario with several major adaptations. To aid the training and evaluation of data-driven methods, we annotate 3,000 chit-chat dialogues (27,198 sentences) with fine-grained sentiment information, including all sentiment expressions, their polarities and the corresponding target mentions. We also annotate an out-of-domain test set of 200 dialogues for robustness evaluation. Besides, we develop multiple baselines based on either pretrained BERT or self-attention for preliminary study. Experimental results show that our BERT-based model has strong performances for both in-domain and out-of-domain datasets, and thorough analysis indicates several potential directions for further improvements.

Transformer benefits from the high parallelization of attention networks in fast training, but it still suffers from slow decoding partially due to the linear dependency O(m) of the decoder self-attention on previous target words at inference. In this paper, we propose a generalized average attention network (AAN+) aiming at speeding up decoding by reducing the dependency from O(m) to O(1). We find that the learned self-attention weights in the decoder follow some patterns which can be approximated via a dynamic structure. Based on this insight, we develop AAN+, extending our previously proposed average attention (Zhang et al., 2018a, AAN) to support more general position- and content-based attention patterns. AAN+ only requires to maintain a small constant number of hidden states during decoding, ensuring its O(1) dependency. We apply AAN+ as a drop-in replacement of the decoder selfattention and conduct experiments on machine translation (with diverse language pairs), table-to-text generation and document summarization. With masking tricks and dynamic programming, AAN+ enables Transformer to decode sentences around 20% faster without largely compromising in the training speed and the generation performance. Our results further reveal the importance of the localness (neighboring words) in AAN+ and its capability in modeling long-range dependency.

Visual Question Answering (VQA) has attracted extensive research focus recently. Along with the ever-increasing data scale and model complexity, the enormous training cost has become an emerging challenge for VQA. In this article, we show such a massive training cost is indeed plague. In contrast, a fine-grained design of the learning paradigm can be extremely beneficial in terms of both training efficiency and model accuracy. In particular, we argue that there exist two essential and unexplored issues in the existing VQA training paradigm that randomly samples data in each epoch, namely, the "difficulty diversity" and the "label redundancy". Concretely, "difficulty diversity" refers to the varying difficulty levels of different question types, while "label redundancy" refers to the redundant and noisy labels contained in individual question type. To tackle these two issues, in this article we propose a fine-grained VQA learning paradigm with an actor-critic based learning agent, termed FG-A1C. Instead of using all training data from scratch, FG-A1C includes a learning agent that adaptively and intelligently schedules the most difficult question types in each training epoch. Subsequently, two curriculum learning based schemes are further designed to identify the most useful data to be learned within each inidividual question type. We conduct extensive experiments on the VQA2.0 and VQA-CP v2 datasets, which demonstrate the significant benefits of our approach. For instance, on VQA-CP v2, with less than 75 percent of the training data, our learning paradigms can help the model achieves better performance than using the whole dataset. Meanwhile, we also shows the effectivenesss of our method in guiding data labeling. Finally, the proposed paradigm can be seamlessly integrated with any cutting-edge VQA models, without modifying their structures.

Currently, the most dominant neural code generation modelsare often equipped with a tree-structured LSTM decoder, which outputs a sequence of actions to construct an Abstract Syntax Tree (AST) via pre-order traversal. However, such a decoder has two obvious drawbacks. First, except for the parent action, other faraway and important history actions rarely contribute to the current decision. Second, it also neglects future actions, which may be crucial for the prediction of the current action. To deal with these issues, in this paper, we propose a novel AST structure enhanced decoder for code generation, which significantly extends the decoder with respect to the above two aspects. First, we introduce an AST information enhanced attention mechanism to fully exploit history actions, of which impacts are further distinguished according to their syntactic distances, action types and relative positions; Second, we jointly model the predictions of current action and its important future action via multi-task learning, where the learned hidden state of the latter can be further leveraged to improve the former. Experimental results on commonly-used datasets demonstrate the effectiveness of our proposed decoder.1

Existing studies for multi-source neural machine translation (NMT) either separately model different source sentences or resort to the conventional single-source NMT by simply concatenating all source sentences. However, there exist two drawbacks in these approaches. First, they ignore the explicit word-level semantic interactions between source sentences, which have been shown effective in the embeddings of multilingual texts. Second, multiple source sentences are simultaneously encoded by an NMT model, which is unable to fully exploit the semantic information of each source sentence. In this paper, we explore multi-stage information interactions for multi-source NMT. Specifically, we first propose a multi-source NMT model that performs information interactions at the encoding stage. Its encoder contains multiple semantic interaction layers, each of which sequentially consists of (1) monolingual semantic interaction sub-layer, which is based on the self-attention mechanism and used to learn word-level monolingual contextual representations of source sentences, and (2) cross-lingual semantic interaction sub-layer, which leverages word alignments to perform fine-grained semantic transitions among hidden states of different source sentences. Furthermore, at the training stage, we introduce a mutual distillation based training framework, where single-source models and ours perform information interactions. Such framework can fully exploit the semantic information of each source sentence to enhance our model. Extensive experimental results on the WMT14 English-German-French dataset show our method exhibits significant improvements upon competitive baselines.

Code generation aims to automatically generate a piece of code given an input natural language utterance. Currently, among dominant models, it is treated as a sequence-to-tree task, where a decoder outputs a sequence of actions corresponding to the pre-order traversal of an Abstract Syntax Tree. However, such a decoder only exploits the pre-order traversal based preceding actions, which are insufficient to ensure correct action predictions. In this paper, we first throughly analyze the context modeling difference between neural code generation models with different traversals based decodings (preorder traversal vs breadth-first traversal), and then propose to introduce a mutual learning framework to jointly train these models. Under this framework, we continuously enhance both two models via mutual distillation, which involves synchronous executions of two one-to-one knowledge transfers at each training step. More specifically, we alternately choose one model as the student and the other as its teacher, and require the student to fit the training data and the action prediction distributions of its teacher. By doing so, both models can fully absorb the knowledge from each other and thus could be improved simultaneously. Experimental results and in-depth analysis on several benchmark datasets demonstrate the effectiveness of our approach. We release our code at https://github.com/DeepLearnXMU/CGML.

Yubin Ge, Ly Dinh, Xiaofeng Liu, Jinsong Su, Ziyao Lu, Ante Wang, Jana Diesner. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Hui Jiang, Chulun Zhou, Fandong Meng, Biao Zhang, Jie Zhou, Degen Huang, Qingqiang Wu, Jinsong Su. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Huan Lin, Liang Yao, Baosong Yang, Dayiheng Liu, Haibo Zhang, Weihua Luo, Degen Huang, Jinsong Su. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Xin Liu, Baosong Yang, Dayiheng Liu, Haibo Zhang, Weihua Luo, Min Zhang, Haiying Zhang, Jinsong Su. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Shaopeng Lai, Ante Wang, Fandong Meng, Jie Zhou, Yubin Ge, Jiali Zeng, Junfeng Yao, Degen Huang, Jinsong Su. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.

Neural Chat Translation (NCT) aims to translate conversational text between speakers of different languages.Despite the promising performance of sentence-level and context-aware neural machine translation models, there still remain limitations in current NCT models because the inherent dialogue characteristics of chat, such as dialogue coherence and speaker personality, are neglected.In this paper, we propose to promote the chat translation by introducing the modeling of dialogue characteristics into the NCT model.To this end, we design four auxiliary tasks including monolingual response generation, cross-lingual response generation, next utterance discrimination, and speaker identification.Together with the main chat translation task, we optimize the NCT model through the training objectives of all these tasks.By this means, the NCT model can be enhanced by capturing the inherent dialogue characteristics, thus generating more coherent and speaker-relevant translations.Comprehensive experiments on four language directions (English⇔German and English⇔Chinese) verify the effectiveness and superiority of the proposed approach.

Conversational discourse structures aim to describe how a dialogue is organized, thus they are helpful for dialogue understanding and response generation. This paper focuses on predicting discourse dependency structures for multi-party dialogues. Previous work adopts incremental methods that take the features from the already predicted discourse relations to help generate the next one. Although the inter-correlations among predictions considered, we find that the error propagation is also very serious and hurts the overall performance. To alleviate error propagation, we propose a Structure Self-Aware (SSA) model, which adopts a novel edge-centric Graph Neural Network (GNN) to update the information between each Elementary Discourse Unit (EDU) pair layer by layer, so that expressive representations can be learned without historical predictions. In addition, we take auxiliary training signals (e.g. structure distillation) for better representation learning. Our model achieves the new state-of-the-art performances on two conversational discourse parsing benchmarks, largely outperforming the previous methods.

As an important text coherence modeling task, sentence ordering aims to coherently organize a given set of unordered sentences. To achieve this goal, the most important step is to effectively capture and exploit global dependencies among these sentences. In this paper, we propose a novel and flexible external knowledge enhanced graph-based neural network for sentence ordering. Specifically, we first represent the input sentences as a graph, where various kinds of relations (i.e., entity-entity, sentence-sentence and entity-sentence) are exploited to make the graph representation more expressive and less noisy. Then, we introduce graph recurrent network to learn semantic representations of the sentences. To demonstrate the effectiveness of our model, we conduct experiments on several benchmark datasets. The experimental results and in-depth analysis show our model significantly outperforms the existing state-of-the-art models.

Owing to its practical significance, multi-domain Neural Machine Translation (NMT) has attracted much attention recently. Recent studies mainly focus on constructing a unified NMT model with mixed-domain training corpora to switch translation between different domains. In these models, the words in the same sentence are not well distinguished, while intuitively, they are related to the sentence domain to varying degrees and thus should exert different effects on the multi-domain NMT model. In this article, we are committed to distinguishing and exploiting different word-level domain contexts for multi-domain NMT. For this purpose, we adopt multi-task learning to jointly model NMT and monolingual attention-based domain classification tasks, improving the NMT model in two ways: 1) One domain classifier and one adversarial domain classifier are introduced to conduct domain classifications of input sentences. During this process, two generated gating vectors are used to produce domain-specific and domain-shared annotations for decoder; 2) We equip decoder with an attentional domain classifier. Then, the derived attentional weights are utilized to refine the model training via word-level cost weighting, so that the impacts of target words can be discriminated by their relevance to sentence domain. Experimental results on several multi-domain translations demonstrate the effectiveness of our model.

Domain adaptation for low-resource dialogue state tracking (DST) is of significance due to the growing diversity of conversation scenarios. In this paper, we propose a novel domain adaptive model-agnostic meta-learning (DAMAML) framework. Under this framework, we equip the DST model with two domain adaptors and a unified parameter generator. The parameter generator takes a domain embedding as input to produce parameters of domain adaptors, which modulate domain-shared initial parameters to the subspace of each domain. In this way, we simultaneously model multiple individual meta-learners with each covering the distribution of one domain, allowing more efficient adaptation. Compared with the conventional MAML, this framework not only is able to seek domain-shared initial parameters that facilitate fast adaptation, but also has better capability to fit a diversified domain distribution. Experimental results and in-depth analysis demonstrate the effectiveness of the proposed framework.

It is known that media outlets, such as CNN and FOX, have intrinsic political bias that is reflected in their news reports. The computational prediction of such bias has broad application prospects. However, the prediction is difficult via directly analyzing the news content without high-level context. In contrast, social signals (e.g., the network structure of media followers) provide inspiring cues to uncover such bias. In this article, we realize the first attempt of predicting the latent bias of media outlets by analyzing their social network structures. In particular, we address two key challenges:network sparsityandlabel sparsity. The network sparsity refers to the partial sampling of the entire follower network in practical analysis and computing, whereas the label sparsity refers to the difficulty of annotating sufficient labels to train the prediction model. To cope with the network sparsity, we propose a hybrid sampling strategy to construct a training corpus that contains network information from micro to macro views. Based on this training corpus, a semi-supervised network embedding approach is proposed to learn low-dimensional yet effective network representations. To deal with the label sparsity, we adopt a graph-based label propagation scheme to supplement the missing links and augment label information for model training. The preceding two steps are iteratively optimized to reinforce each other. We further collect a large-scale dataset containing social networks of 10 media outlets together with about 300,000 followers and more than 5 million connections. Over this dataset, we compare our model to a range of state of the art. Superior performance gains demonstrate the merits of the proposed approach. More importantly, the experimental results and analyses confirm the validity of our approach for the computerized prediction of media bias.

Lacking robustness is a serious problem for Machine Reading Comprehension (MRC) models. To alleviate this problem, one of the most promising ways is to augment the training dataset with sophisticated designed adversarial examples. Generally, those examples are created by rules according to the observed patterns of successful adversarial attacks. Since the types of adversarial examples are innumerable, it is not adequate to manually design and enrich training data to defend against all types of adversarial attacks. In this paper, we propose a novel robust adversarial training approach to improve the robustness of MRC models in a more generic way. Given an MRC model well-trained on the original dataset, our approach dynamically generates adversarial examples based on the parameters of current model and further trains the model by using the generated examples in an iterative schedule. When applied to the state-of-the-art MRC models, including QANET, BERT and ERNIE2.0, our approach obtains significant and comprehensive improvements on 5 adversarial datasets constructed in different ways, without sacrificing the performance on the original SQuAD development set. Moreover, when coupled with other data augmentation strategy, our approach further boosts the overall performance on adversarial datasets and outperforms the state-of-the-art methods.

Dominant sentence ordering models use a pointer network decoder to generate ordering sequences in a left-to-right fashion. However, such a decoder only exploits the noisy left-side encoded context, which is insufficient to ensure correct sentence ordering. To address this deficiency, we propose to enhance the pointer network decoder by using two pairwise ordering prediction modules: The FUTURE module predicts the relative orientations of other unordered sentences with respect to the candidate sentence, and the HISTORY module measures the local coherence between several (e.g., 2) previously ordered sentences and the candidate sentence, without the influence of noisy left-side context. Using the pointer mechanism, we then incorporate this dynamically generated information into the decoder as a supplement to the left-side context for better predictions. On several commonly-used datasets, our model significantly outperforms other baselines, achieving the state-of-the-art performance. Further analyses verify that pairwise ordering predictions indeed provide extra useful context as expected, leading to better sentence ordering. We also evaluate our sentence ordering models on a downstream task, multi-document summarization, and the summaries reordered by our model achieve the best coherence scores. Our code is available at https://github.com/DeepLearnXMU/Pairwise.git.

Simile recognition is to detect simile sentences and to extract simile components, i.e., tenors and vehicles. It involves two subtasks: simile sentence classification and simile component extraction. Recent work has shown that standard multitask learning is effective for Chinese simile recognition, but it is still uncertain whether the mutual effects between the subtasks have been well captured by simple parameter sharing. We propose a novel cyclic multitask learning framework for neural simile recognition, which stacks the subtasks and makes them into a loop by connecting the last to the first. It iteratively performs each subtask, taking the outputs of the previous subtask as additional inputs to the current one, so that the interdependence between the subtasks can be better explored. Extensive experiments show that our framework significantly outperforms the current state-of-the-art model and our carefully designed baselines, and the gains are still remarkable using BERT. Source Code of this paper are available on https://github.com/DeepLearnXMU/Cyclic.

The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs.As a crucial defect, the current state-of-the-art models may mess up or even drop the core structural information of input graphs when generating outputs.We propose to tackle this problem by leveraging richer training signals that can guide our model for preserving input information.In particular, we introduce two types of autoencoding losses, each individually focusing on different aspects (a.k.a.views) of input graphs.The losses are then back-propagated to better calibrate our model via multi-task training.Experiments on two benchmarks for graph-to-text generation show the effectiveness of our approach over a state-of-the-art baseline.Our code is available at http://github.com/ Soistesimmer/AMR-multiview.

Multi-modal neural machine translation (NMT) aims to translate source sentences into a target language paired with images. However, dominant multi-modal NMT models do not fully exploit fine-grained semantic correspondences between semantic units of different modalities, which have potential to refine multi-modal representation learning. To deal with this issue, in this paper, we propose a novel graph-based multi-modal fusion encoder for NMT. Specifically, we first represent the input sentence and image using a unified multi-modal graph, which captures various semantic relationships between multi-modal semantic units (words and visual objects). We then stack multiple graph-based multi-modal fusion layers that iteratively perform semantic interactions to learn node representations. Finally, these representations provide an attention-based context vector for the decoder. We evaluate our proposed encoder on the Multi30K datasets. Experimental results and in-depth analysis show the superiority of our multi-modal NMT model.

Unsupervised style transfer aims to change the style of an input sentence while preserving its original content without using parallel training data. In current dominant approaches, owing to the lack of fine-grained control on the influence from the target style, they are unable to yield desirable output sentences. In this paper, we propose a novel attentional sequence-to-sequence (Seq2seq) model that dynamically exploits the relevance of each output word to the target style for unsupervised style transfer. Specifically, we first pretrain a style classifier, where the relevance of each input word to the original style can be quantified via layer-wise relevance propagation. In a denoising auto-encoding manner, we train an attentional Seq2seq model to reconstruct input sentences and repredict word-level previously-quantified style relevance simultaneously. In this way, this model is endowed with the ability to automatically predict the style relevance of each output word. Then, we equip the decoder of this model with a neural style component to exploit the predicted wordlevel style relevance for better style transfer. Particularly, we fine-tune this model using a carefully-designed objective function involving style transfer, style relevance consistency, content preservation and fluency modeling loss terms. Experimental results show that our proposed model achieves state-of-the-art performance in terms of both transfer accuracy and content preservation.

The lack of sufficient training data in many domains, poses a major challenge to the construction of domain-specific machine reading comprehension (MRC) models with satisfying performance. In this paper, we propose a novel iterative multi-source mutual knowledge transfer framework for MRC. As an extension of the conventional knowledge transfer with one-to-one correspondence, our framework focuses on the many-to-many mutual transfer, which involves synchronous executions of multiple many-to-one transfers in an iterative manner.Specifically, to update a target-domain MRC model, we first consider other domain-specific MRC models as individual teachers, and employ knowledge distillation to train a multi-domain MRC model, which is differentially required to fit the training data and match the outputs of these individual models according to their domain-level similarities to the target domain. After being initialized by the multi-domain MRC model, the target-domain MRC model is fine-tuned to match both its training data and the output of its previous best model simultaneously via knowledge distillation. Compared with previous approaches, our framework can continuously enhance all domain-specific MRC models by enabling each model to iteratively and differentially absorb the domain-shared knowledge from others. Experimental results and in-depth analyses on several benchmark datasets demonstrate the effectiveness of our framework.

Multimodal machine translation (MMT), which mainly focuses on enhancing text-only translation with visual features, has attracted considerable attention from both computer vision and natural language processing communities. Most current MMT models resort to attention mechanism, global context modeling or multimodal joint representation learning to utilize visual features. However, the attention mechanism lacks sufficient semantic interactions between modalities while the other two provide fixed visual context, which is unsuitable for modeling the observed variability when generating translation. To address the above issues, in this paper, we propose a novel Dynamic Context-guided Capsule Network (DCCN) for MMT. Specifically, at each timestep of decoding, we first employ the conventional source-target attention to produce a timestep-specific source-side context vector. Next, DCCN takes this vector as input and uses it to guide the iterative extraction of related visual features via a context-guided dynamic routing mechanism. Particularly, we represent the input image with global and regional visual features, we introduce two parallel DCCNs to model multimodal context vectors with visual features at different granularities. Finally, we obtain two multimodal context vectors, which are fused and incorporated into the decoder for the prediction of the target word. Experimental results on the Multi30K dataset of English-to-German and English-to-French translation demonstrate the superiority of DCCN. Our code is available on https://github.com/DeepLearnXMU/MM-DCCN.

Referring expression segmentation (RES) aims to segment the target instance in a given image according to a natural language expression. Its main challenge lies in how to quickly and accurately align the text expression to the referred visual instances. In this paper, we focus on addressing this issue by proposing a Cascade Grouped Attention Network (CGAN) with two innovative designs: Cascade Grouped Attention (CGA) and Instance-level Attention (ILA) loss. Specifically, CGA is used to perform step-wise reasoning over the entire image to perceive the differences between instances accurately yet efficiently, so as to identify the referent. ILA loss is further embedded into each step of CGA to directly supervise the attention modeling, which improves the alignments between the text expression and the visual instances. Through these two novel designs, CGAN can achieve the high efficiency of one-stage RES while possessing a strong reasoning ability comparable to the two-stage methods. To validate our model, we conduct extensive experiments on three RES benchmark datasets and achieve significant performance gains over existing one-stage and multi-stage models

In this paper, we propose a cross-modal network architecture search (NAS) algorithm for VQA, termed as k-Armed Bandit based NAS (KAB-NAS). KAB-NAS regards the design of each layer as a k-armed bandit problem and updates the preference of each candidate via numerous samplings in a single-shot search framework. To establish an effective search space, we further propose a new architecture termed Automatic Graph Attention Network (AGAN), and extend the popular self-attention layer with three graph structures, denoted as dense-graph, co-graph and separate-graph.These graph layers are used to form the direction of information propagation in the graph network, and their optimal combinations are searched by KAB-NAS. To evaluate KAB-NAS and AGAN, we conduct extensive experiments on two VQA benchmark datasets, i.e., VQA2.0 and GQA, and also test AGAN with the popular BERT-style pre-training. The experimental results show that with the help of KAB-NAS, AGAN can achieve the state-of-the-art performance on both benchmark datasets with much fewer parameters and computations.

Deepening neural models has been proven very successful in improving the model's capacity when solving complex learning tasks, such as the machine translation task. Previous efforts on deep neural machine translation mainly focus on the encoder and the decoder, while little on the attention mechanism. However, the attention mechanism is of vital importance to induce the translation correspondence between different languages where shallow neural networks are relatively insufficient, especially when the encoder and decoder are deep. In this paper, we propose a deep attention model (DeepAtt). Based on the low-level attention information, DeepAtt is capable of automatically determining what should be passed or suppressed from the corresponding encoder layer so as to make the distributed representation appropriate for high-level attention and translation. We conduct experiments on NIST Chinese-English, WMT English-German, and WMT English-French translation tasks, where, with five attention layers, DeepAtt yields very competitive performance against the state-of-the-art results. We empirically find that with an adequate increase of attention layers, DeepAtt tends to produce more accurate attention weights. An in-depth analysis on the translation of important context words further reveals that DeepAtt significantly improves the faithfulness of system translations.

Exploiting semantic interactions between the source and target linguistic items at different levels of granularity is crucial for generating compact vector representations for bilingual phrases. To achieve this, we propose alignment-supervised bidimensional attention-based recursive autoencoders (ABattRAE) in this paper. ABattRAE first individually employs two recursive autoencoders to recover hierarchical tree structures of bilingual phrase, and treats the subphrase covered by each node on the tree as a linguistic item. Unlike previous methods, ABattRAE introduces a bidimensional attention network to measure the semantic matching degree between linguistic items of different languages, which enables our model to integrate information from all nodes by dynamically assigning varying weights to their corresponding embeddings. To ensure the accuracy of the generated attention weights in the attention network, ABattRAE incorporates word alignments as supervision signals to guide the learning procedure. Using the general stochastic gradient descent algorithm, we train our model in an end-to-end fashion, where the semantic similarity of translation equivalents is maximized while the semantic similarity of nontranslation pairs is minimized. Finally, we incorporate a semantic feature based on the learned bilingual phrase representations into a machine translation system for better translation selection. Experimental results on NIST Chinese-English and WMT English-German test sets show that our model achieves substantial improvements of up to 2.86 and 1.09 BLEU points over the baseline, respectively. Extensive in-depth analyses demonstrate the superiority of our model in learning bilingual phrase embeddings.

Neural machine translation (NMT) heavily relies on context vectors generated by an attention network to predict target words. In practice, we observe that the context vectors for different target words are quite similar to one another and translations with such nondiscriminatory context vectors tend to be degenerative. We ascribe this similarity to the invariant source representations that lack dynamics across decoding steps. In this article, we propose a novel gated recurrent unit (GRU)-gated attention model (GAtt) for NMT. By updating the source representations with the previous decoder state via a GRU, GAtt enables translation-sensitive source representations that then contribute to discriminative context vectors. We further propose a variant of GAtt by swapping the input order of the source representations and the previous decoder state to the GRU. Experiments on the NIST Chinese-English, WMT14 English-German, and WMT17 English-German translation tasks show that the two GAtt models achieve significant improvements over the vanilla attention-based NMT. Further analyses on the attention weights and context vectors demonstrate the effectiveness of GAtt in enhancing the discriminating capacity of representations and handling the challenging issue of overtranslation.

In this paper, we uncover the issue of knowledge inertia in visual question answering (VQA), which commonly exists in most VQA models and forces the models to mainly rely on the question content to “guess” answer, without regard to the visual information. Such an issue not only impairs the performance of VQA models, but also greatly reduces the credibility of the answer prediction. To this end, simply highlighting the visual features in the model is undoable, since the prediction is built upon the joint modeling of two modalities and largely influenced by the data distribution. In this paper, we propose a Pairwise Inconformity Learning (PIL) to tackle the issue of knowledge inertia. In particular, PIL takes full advantage of the similar image pairs with diverse answers to an identical question provided in VQA2.0 dataset. It builds a multi-modal embedding space to project pos./neg. feature pairs, upon which word vectors of answers are modeled as anchors. By doing so, PIL strengthens the importance of visual features in prediction with a novel dynamic-margin based triplet loss that efficiently increases the semantic discrepancies between pos./neg. image pairs. To verify the proposed PIL, we plug it on a baseline VQA model as well as a set of recent VQA models, and conduct extensive experiments on two benchmark datasets, i.e., VQA1.0 and VQA2.0. Experimental results show that PIL can boost the accuracy of the existing VQA models (1.56%-2.93% gain) with a negligible increase in parameters (0.85%-5.4% parameters). Qualitative results also reveal the elimination of knowledge inertia in the existing VQA models after implementing our PIL.

In visual question answering (VQA), recent advances have well advocated the use of attention mechanism to precisely link the question to the potential answer areas. As the difficulty of the question increases, more VQA models adopt multiple attention layers to capture the deeper visual-linguistic correlation. But a negative consequence is the explosion of parameters, which makes the model vulnerable to over-fitting, especially when limited training examples are given. In this paper, we propose an extremely compact alternative to this static multi-layer architecture towards accurate yet efficient attention modeling, termed as Dynamic Capsule Attention (CapsAtt). Inspired by the recent work of Capsule Network, CapsAtt treats visual features as capsules and obtains the attention output via dynamic routing, which updates the attention weights by calculating coupling coefficients between the underlying and output capsules. Meanwhile, CapsAtt also discards redundant projection matrices to make the model much more compact. We quantify CapsAtt on three benchmark VQA datasets, i.e., COCO-QA, VQA1.0 and VQA2.0. Compared to the traditional multi-layer attention model, CapsAtt achieves significant improvements of up to 4.1%, 5.2% and 2.2% on three datasets, respectively. Moreover, with much fewer parameters, our approach also yields competitive results compared to the latest VQA models. To further verify the generalization ability of CapsAtt, we also deploy it on another challenging multi-modal task of image captioning, where state-of-the-art performance is achieved with a simple network structure.

In aspect-level sentiment classification (ASC), it is prevalent to equip dominant neural models with attention mechanisms, for the sake of acquiring the importance of each context word on the given aspect. However, such a mechanism tends to excessively focus on a few frequent words with sentiment polarities, while ignoring infrequent ones. In this paper, we propose a progressive self-supervised attention learning approach for neural ASC models, which automatically mines useful attention supervision information from a training corpus to refine attention mechanisms. Specifically, we iteratively conduct sentiment predictions on all training instances. Particularly, at each iteration, the context word with the maximum attention weight is extracted as the one with active/misleading influence on the correct/incorrect prediction of every instance, and then the word itself is masked for subsequent iterations. Finally, we augment the conventional training objective with a regularization term, which enables ASC models to continue equally focusing on the extracted active context words while decreasing weights of those misleading ones. Experimental results on multiple datasets show that our proposed approach yields better attention mechanisms, leading to substantial improvements over the two state-of-the-art neural ASC models. Source code and trained models are available at https://github.com/DeepLearnXMU/PSSAttention.

Linfeng Song, Yue Zhang, Daniel Gildea, Mo Yu, Zhiguo Wang, Jinsong Su. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong, Lei Li. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Jiali Zeng, Yang Liu, Jinsong Su, Yubing Ge, Yaojie Lu, Yongjing Yin, Jiebo Luo. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

The cross-modality topic detection in social media retains as an open problem mainly due to the difficulty of dealing with modality independence and modality missing. In this paper, we present a novel Deep Topical Correlation Analysis (DTCA) approach, which achieves robust and accurate topic detecting for micro-blogs and handles aforementioned challenges simultaneously. In particular, bidirectional recurrent neural networks and convolutional neural networks are used to learn deep textual and visual features, respectively. Then a Canonical Correlation Analysis based fusion scheme is proposed, which has two innovations to deal with both two problems mentioned above. We further release a large-scale cross-modal twitter dataset for topic detection. Extensive and quantitative evaluations are conducted with comparisons to several state-of-the-arts and alternative approaches on this dataset. Significant performance gains are reported to demonstrate the merits of proposed approach.

Benefiting from the excellent ability of neural networks on learning semantic representations, existing studies for entity linking (EL) have resorted to neural networks to exploit both the local mention-to-entity compatibility and the global interdependence between different EL decisions for target entity disambiguation. However, most neural collective EL methods depend entirely upon neural networks to automatically model the semantic dependencies between different EL decisions, which lack of the guidance from external knowledge. In this paper, we propose a novel end-to-end neural network with recurrent random-walk layers for collective EL, which introduces external knowledge to model the semantic interdependence between different EL decisions. Specifically, we first establish a model based on local context features, and then stack random-walk layers to reinforce the evidence for related EL decisions into high-probability decisions, where the semantic interdependence between candidate entities is mainly induced from an external knowledge base. Finally, a semantic regularizer that preserves the collective EL decisions consistency is incorporated into the conventional objective function, so that the external knowledge base can be fully exploited in collective EL decisions. Experimental results and in-depth analysis on various datasets show that our model achieves better performance than other state-of-the-art models. Our code and data are released at https://github.com/DeepLearnXMU/RRWEL.

Sentence ordering is to restore the original paragraph from a set of sentences. It involves capturing global dependencies among sentences regardless of their input order. In this paper, we propose a novel and flexible graph-based neural sentence ordering model, which adopts graph recurrent network \citep{Zhang:acl18} to accurately learn semantic representations of the sentences. Instead of assuming connections between all pairs of input sentences, we use entities that are shared among multiple sentences to make more expressive graph representations with less noise. Experimental results show that our proposed model outperforms the existing state-of-the-art systems on several benchmark datasets, demonstrating the effectiveness of our model. We also conduct a thorough analysis on how entities help the performance. Our code is available at https://github.com/DeepLearnXMU/NSEG.git.

We address the problem of video moment localization with natural language, i.e. localizing a video segment described by a natural language sentence. While most prior work focuses on grounding the query as a whole, temporal dependencies and reasoning between events within the text are not fully considered. In this paper, we propose a novel Temporal Compositional Modular Network (TCMN) where a tree attention network first automatically decomposes a sentence into three descriptions with respect to the main event, context event and temporal signal. Two modules are then utilized to measure the visual similarity and location similarity between each segment and the decomposed descriptions. Moreover, since the main event and context event may rely on different modalities (RGB or optical flow), we use late fusion to form an ensemble of four models, where each model is independently trained by one combination of the visual input. Experiments show that our model outperforms the state-of-the-art methods on the TEMPO dataset.

Abstract It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation models. On the other hand, little work has been done on leveraging semantics for neural machine translation (NMT). In this work, we study the usefulness of AMR (abstract meaning representation) on NMT. Experiments on a standard English-to-German dataset show that incorporating AMR as additional knowledge can significantly improve a strong attention-based sequence-to-sequence neural translation model.

Although neural machine translation (NMT) has certain capability to implicitly learn semantic information of sentences, we explore and show that Part-of-Speech (POS) tags can be explicitly incorporated into the attention mechanism of NMT effectively to yield further improvements. In this article, we propose an NMT model with tag-enhanced attention mechanism. In our model, NMT and POS tagging are jointly modeled via multi-task learning. Besides following common practice to enrich encoder annotations by introducing predicted source POS tags, we exploit predicted target POS tags to refine attention model in a coarse-to-fine manner. Specifically, we first implement a coarse attention operation solely on source annotations and target hidden state, where the produced context vector is applied to update target hidden state used for target POS tagging. Then, we perform a fine attention operation that extends the coarse one by further exploiting the predicted target POS tags. Finally, we facilitate word prediction by simultaneously utilizing the context vector from fine attention and the predicted target POS tags. Experimental results and further analyses on Chinese-English and Japanese-English translation tasks demonstrate the superiority of our proposed model over the conventional NMT models. We release our code at https://github.com/middlekisser/PEA-NMT.git.

Although future context is widely regarded useful for word prediction in machine translation, it is quite difficult in practice to incorporate it into neural machine translation. In this paper, we propose a future-aware knowledge distillation framework (FKD) to address this issue. In the FKD framework, we learn to distill future knowledge from a backward neural language model (teacher) to future-aware vectors (student) during the training phase. The future-aware vector for each word position is computed in a bridge network and optimized towards the corresponding hidden state in the backward neural language model via a knowledge distillation mechanism. We further propose an algorithm to jointly train the neural machine translation model, neural language model and knowledge distillation module end-to-end. The learned future-aware vectors are incorporated into the attention layer of the decoder to provide full-range context information during the decoding phase. Experiments on the NIST Chinese-English and WMT English-German translation tasks show that the proposed method significantly improves translation quality and word alignment.

Partially inspired by successful applications of variational recurrent neural networks, we propose a novel variational recurrent neural machine translation (VRNMT) model in this paper. Different from the variational NMT, VRNMT introduces a series of latent random variables to model the translation procedure of a sentence in a generative way, instead of a single latent variable. Specifically, the latent random variables are included into the hidden states of the NMT decoder with elements from the variational autoencoder. In this way, these variables are recurrently generated, which enables them to further capture strong and complex dependencies among the output translations at different timesteps. In order to deal with the challenges in performing efficient posterior inference and large-scale training during the incorporation of latent variables, we build a neural posterior approximator, and equip it with a reparameterization technique to estimate the variational lower bound. Experiments on Chinese-English and English-German translation tasks demonstrate that the proposed model achieves significant improvements over both the conventional and variational NMT models.

The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-to-right manner, leaving the target-side contexts generated from right to left unexploited during translation. In this paper, we equip the conventional attentional encoder-decoder NMT framework with a backward decoder, in order to explore bidirectional decoding for NMT. Attending to the hidden state sequence produced by the encoder, our backward decoder first learns to generate the target-side hidden state sequence from right to left. Then, the forward decoder performs translation in the forward direction, while in each translation prediction timestep, it simultaneously applies two attention models to consider the source-side and reverse target-side hidden states, respectively. With this new architecture, our model is able to fully exploit source- and target-side contexts to improve translation quality altogether. Experimental results on NIST Chinese-English and WMT English-German translation tasks demonstrate that our model achieves substantial improvements over the conventional NMT by 3.14 and 1.38 BLEU points, respectively. The source code of this work can be obtained from https://github.com/DeepLearnXMU/ABDNMT.

With parallelizable attention networks, the neural Transformer is very fast to train.However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow.To alleviate this issue, we propose an average attention network as an alternative to the self-attention network in the decoder of the neural Transformer.The average attention network consists of two layers, with an average layer that models dependencies on previous positions and a gating layer that is stacked over the average layer to enhance the expressiveness of the proposed attention network.We apply this network on the decoder part of the neural Transformer to replace the original target-side self-attention model.With masking tricks and dynamic programming, our model enables the neural Transformer to decode sentences over four times faster than its original version with almost no loss in training time and translation performance.We conduct a series of experiments on WMT17 translation tasks, where on 6 different language pairs, we obtain robust and consistent speed-ups in decoding.1

A great proportion of sequence-to-sequence (Seq2Seq) models for Neural Machine Translation (NMT) adopt Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. As the studies of linguistics have proved that language is not linear word sequence but sequence of complex structure, translation at each step should be conditioned on the whole target-side context. To tackle the problem, we propose a new NMT model that decodes the sequence with the guidance of its structural prediction of the context of the target sequence. Our model generates translation based on the structural prediction of the target-side context so that the translation can be freed from the bind of sequential order. Experimental results demonstrate that our model is more competitive compared with the state-of-the-art methods, and the analysis reflects that our model is also robust to translating sentences of different lengths and it also reduces repetition with the instruction from the target-side context for decoding.

Neural machine translation with source-side attention have achieved remarkable performance. however, there has been little work exploring to attend to the target-side which can potentially enhance the memory capbility of NMT. We reformulate a Decoding History Enhanced Attention mechanism (DHEA) to render NMT model better at selecting both source-side and target-side information. DHA enables dynamic control of the ratios at which source and target contexts contribute to the generation of target words, offering a way to weakly induce structure relations among both source and target tokens. It also allows training errors to be directly back-propagated through short-cut connections and effectively alleviates the gradient vanishing problem. The empirical study on Chinese-English translation shows that our model with proper configuration can improve by 0:9 BLEU upon Transformer and the best reported results in the dataset. On WMT14 English-German task and a larger WMT14 English-French task, our model achieves comparable results with the state-of-the-art.

Most image captioning models focus on one-line (single image) captioning, where the correlations like relevance and diversity among group images (e.g., within the same album or event) are simply neglected, resulting in less accurate and diverse captions. Recent works mainly consider imposing the diversity during the online inference only, which neglect the correlation among visual structures in offline training. In this paper, we propose a novel group-based image captioning scheme (termed GroupCap), which jointly models the structured relevance and diversity among group images towards an optimal collaborative captioning. In particular, we first propose a visual tree parser (VP-Tree) to construct the structured semantic correlations within individual images. Then, the relevance and diversity among images are well modeled by exploiting the correlations among their tree structures. Finally, such correlations are modeled as constraints and sent into the LSTM-based captioning generator. We adopt an end-to-end formulation to train the visual tree parser, the structured relevance and diversity constraints, as well as the LSTM based captioning model jointly. To facilitate quantitative evaluation, we further release two group captioning datasets derived from the MS-COCO benchmark, serving as the first of their kind. Quantitative results show that the proposed GroupCap model outperforms the state-of-the-art and alternative approaches.

With great practical value, the study of Multidomain Neural Machine Translation (NMT) mainly focuses on using mixed-domain parallel sentences to construct a unified model that allows translation to switch between different domains.Intuitively, words in a sentence are related to its domain to varying degrees, so that they will exert disparate impacts on the multi-domain NMT modeling.Based on this intuition, in this paper, we devote to distinguishing and exploiting word-level domain contexts for multi-domain NMT.To this end, we jointly model NMT with monolingual attention-based domain classification tasks and improve NMT as follows: 1) Based on the sentence representations produced by a domain classifier and an adversarial domain classifier, we generate two gating vectors and use them to construct domain-specific and domain-shared annotations, for later translation predictions via different attention models; 2) We utilize the attention weights derived from target-side domain classifier to adjust the weights of target words in the training objective, enabling domain-related words to have greater impacts during model training.Experimental results on Chinese-English and English-French multi-domain translation tasks demonstrate the effectiveness of the proposed model.Source codes of this paper are available on Github https://github.com/DeepLearnXMU/WDCNMT.

In this paper, we propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation.The recurrent units of ATR are heavily simplified to have the smallest number of weight matrices among units of all existing gated RNNs.With the simple addition and subtraction operation, we introduce a twin-gated mechanism to build input and forget gates which are highly correlated.Despite this simplification, the essential non-linearities and capability of modeling long-distance dependencies are preserved.Additionally, the proposed ATR is more transparent than LSTM/GRU due to the simplification.Forward self-attention can be easily established in ATR, which makes the proposed network interpretable.Experiments on WMT14 translation tasks demonstrate that ATR-based neural machine translation can yield competitive performance on English-German and English-French language pairs in terms of both translation quality and speed.Further experiments on NIST Chinese-English translation, natural language inference and Chinese word segmentation verify the generality and applicability of ATR on different natural language processing tasks.

A lack of labeled corpora obstructs the research progress on implicit discourse relation recognition (DRR) for Chinese, while there are some available discourse corpora in other languages, such as English. In this paper, we propose a cross-lingual implicit DRR framework that exploits an available English corpus for the Chinese DRR task. We use machine translation to generate Chinese instances from a labeled English discourse corpus. In this way, each instance has two independent views: Chinese and English views. Then we train two classifiers in Chinese and English in a co-training way, which exploits unlabeled Chinese data to implement better implicit DRR for Chinese. Experimental results demonstrate the effectiveness of our method.

Although sequence-to-sequence attentional neural machine translation (NMT) has achieved great progress recently, it is confronted with two challenges: learning optimal model parameters for long parallel sentences and well exploiting different scopes of contexts. In this paper, partially inspired by the idea of segmenting a long sentence into short clauses, each of which can be easily translated by NMT, we propose a hierarchy-to-sequence attentional NMT model to handle these two challenges. Our encoder takes the segmented clause sequence as input and explores a hierarchical neural network structure to model words, clauses, and sentences at different levels, particularly with two layers of recurrent neural networks modeling semantic compositionality at the word and clause level. Correspondingly, the decoder sequentially translates segmented clauses and simultaneously applies two types of attention models to capture contexts of interclause and intraclause for translation prediction. In this way, we can not only improve parameter learning, but also well explore different scopes of contexts for translation. Experimental results on Chinese-English and English-German translation demonstrate the superiorities of the proposed model over the conventional NMT model.

Predicting sentiments of multimodal microblogs composed of text, image, and emoticon have attracted ever-increasing research focus recently. The key challenge lies in the difficulty of collecting a sufficient amount of training labels to train a discriminative model for multimodal prediction. One potential solution is to exploit the labels collected from social media users, which is, however, restricted by the negative effect of label noise. Besides, we have quantitatively found that sentiments in different modalities may be independent, which disables the usage of previous multimodal sentiment analysis schemes in our problem. In this paper, we introduce a weakly supervised multimodal deep learning (WS-MDL) scheme toward robust and scalable sentiment prediction. WS-MDL learns convolutional neural networks iteratively and selectively from “weak” emoticon labels, which are cheaply available and noise containing. In particular, to filter out the label noise and to capture the modality dependency, a probabilistic graphical model is introduced to simultaneously learn discriminative multimodal descriptors and infer the confidence of label noise. Extensive evaluations are conducted in a million-scale, real-world microblog sentiment dataset crawled from Sina Weibo. We have validated the merits of the proposed scheme by quantitatively showing its superior performance over several state-of-the-art and alternative approaches.

Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences.However, for languages without natural word delimiters (e.g., Chinese) where input sentences have to be tokenized first,conventional NMT is confronted with two issues:1) it is difficult to find an optimal tokenization granularity for source sentence modelling, and2) errors in 1-best tokenizations may propagate to the encoder of NMT.To handle these issues, we propose word-lattice based Recurrent Neural Network (RNN) encoders for NMT,which generalize the standard RNN to word lattice topology.The proposed encoders take as input a word lattice that compactly encodes multiple tokenizations, and learn to generate new hidden states from arbitrarily many inputs and hidden states in preceding time steps.As such, the word-lattice based encoders not only alleviate the negative impact of tokenization errors but also are more expressive and flexible to embed input sentences.Experiment results on Chinese-English translation demonstrate the superiorities of the proposed encoders over the conventional encoder.

In this paper, we propose a bidimensional attention based recursiveautoencoder (BattRAE) to integrate clues and sourcetargetinteractions at multiple levels of granularity into bilingualphrase representations. We employ recursive autoencodersto generate tree structures of phrases with embeddingsat different levels of granularity (e.g., words, sub-phrases andphrases). Over these embeddings on the source and targetside, we introduce a bidimensional attention network to learntheir interactions encoded in a bidimensional attention matrix,from which we extract two soft attention weight distributionssimultaneously. These weight distributions enableBattRAE to generate compositive phrase representations viaconvolution. Based on the learned phrase representations, wefurther use a bilinear neural model, trained via a max-marginmethod, to measure bilingual semantic similarity. To evaluatethe effectiveness of BattRAE, we incorporate this semanticsimilarity as an additional feature into a state-of-the-art SMTsystem. Extensive experiments on NIST Chinese-English testsets show that our model achieves a substantial improvementof up to 1.63 BLEU points on average over the baseline.

Image captioning has attracted ever-increasing research attention in multimedia and computer vision. To encode the visual content, existing approaches typically utilize the off-the-shelf deep Convolutional Neural Network (CNN) model to extract visual features, which are sent to Recurrent Neural Network (RNN) based textual generators to output word sequence. Some methods encode visual objects and scene information with attention mechanism more recently. Despite the promising progress, one distinct disadvantage lies in distinguishing and modeling key semantic entities and their relations, which are in turn widely regarded as the important cues for us to describe image content. In this paper, we propose a novel image captioning model, termed StructCap. It parses a given image into key entities and their relations organized in a visual parsing tree, which is transformed and embedded under an encoder-decoder framework via visual attention. We give an end-to-end formulation to facilitate joint training of visual tree parser, structured semantic attention and RNN-based captioning modules. Experimental results on two public benchmarks, Microsoft COCO and Flickr30K, show that the proposed StructCap model outperforms the state-of-the-art approaches under various standard evaluation metrics.

Most of existing works in visual question answering (VQA) are dedicated to improving the performance of answer predictions, while leaving the explanation of answering unexploited. We argue that, exploiting the explanations of question answering not only makes VQA explainable, but also quantitatively improves the prediction performance. In this paper, we propose a novel network architecture, termed Neural Pivot Network (NPN), towards simultaneous VQA and generating explanations in a multi-task learning architecture. NPN is trained by using both image-caption and image-question-answer pairs. In principle, CNN-based deep visual features are extracted and sent to both the VQA channel and the captioning module, the latter of which serves as a pivot to bridge the source image module to the target QA predictor. Such an innovative design enables us to introduce large-scale image-captioning training sets, e.g., MS-COCO Caption and Visual Genome Caption, together with cutting-edge image captioning models to benefit VQA learning. Quantitatively, the proposed NPN performs significantly better than alternatives and state-of-the-art schemes trained on VQA datasets only. Besides, by investigating the by-product of experiments, in-depth digests can be provided along with the answers.

Neural machine translation (NMT) heavily relies on its encoder to capture the underlying meaning of a source sentence so as to generate a faithful translation. However, most NMT encoders are built upon either unidirectional or bidirectional recurrent neural networks, which either do not deal with future context or simply concatenate the history and future context to form context-dependent word representations, implicitly assuming the independence of the two types of contextual information. In this paper, we propose a novel context-aware recurrent encoder (CAEncoder), as an alternative to the widely-used bidirectional encoder, such that the future and history contexts can be fully incorporated into the learned source representations. Our CAEncoder involves a two-level hierarchy: The bottom level summarizes the history information, whereas the upper level assembles the summarized history and future context into source representations. Additionally, CAEncoder is as efficient as the bidirectional RNN encoder in terms of both training and decoding. Experiments on both Chinese-English and English-German translation tasks show that CAEncoder achieves significant improvements over the bidirectional RNN encoder on a widely-used NMT system.

Estimating similarities at different levels of linguistic units, such as words, sub-phrases and phrases, is helpful for measuring semantic similarity of an entire bilingual phrase. In this paper, we propose a convolution-enhanced bilingual recursive neural network (ConvBRNN), which not only exploits word alignments to guide the generation of phrase structures but also integrates multiple-level information of the generated phrase structures into bilingual semantic modeling. In order to accurately learn the semantic hierarchy of a bilingual phrase, we develop a recursive neural network to constrain the learned bilingual phrase structures to be consistent with word alignments. Upon the generated source and target phrase structures, we stack a convolutional neural network to integrate vector representations of linguistic units on the structures into bilingual phrase embeddings. After that, we fully incorporate information of different linguistic units into a bilinear semantic similarity model. We introduce two max-margin losses to train the ConvBRNN model: one for the phrase structure inference and the other for the semantic similarity model. Experiments on NIST Chinese-English translation tasks demonstrate the high quality of the generated bilingual phrase structures with respect to word alignments and the effectiveness of learned semantic similarities on machine translation.

Parallel sentence representations are important for bilingual and cross-lingual tasks in natural language processing. In this paper, we explore a bilingual autoencoder approach to model parallel sentences. We extract sentence-level global descriptors (e.g. min, max) from word embeddings, and construct two monolingual autoencoders over these descriptors on the source and target language. In order to tightly connect the two autoencoders with bilingual correspondences, we force them to share the same decoding parameters and minimize a corpus-level semantic distance between the two languages. Being optimized towards a joint objective function of reconstruction and semantic errors, our bilingual antoencoder is able to learn continuous-valued latent representations for parallel sentences. Experiments on both intrinsic and extrinsic evaluations on statistical machine translation tasks show that our autoencoder achieves substantial improvements over the baselines.

To alleviate the shortage of labeled data, we propose to use bilingually-constrained synthetic implicit data for implicit discourse relation recognition.These data are extracted from a bilingual sentence-aligned corpus according to the implicit/explicit mismatch between different languages.Incorporating these data via a multi-task neural network model achieves significant improvements over baselines, on both the English PDTB and Chinese CDTB data sets.

Models of neural machine translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence.In this paper, we propose a variational model to learn this conditional distribution for neural machine translation: a variational encoderdecoder model that can be trained end-to-end.Different from the vanilla encoder-decoder model that generates target translations from hidden representations of source sentences alone, the variational model introduces a continuous latent variable to explicitly model underlying semantics of source sentences and to guide the generation of target translations.In order to perform efficient posterior inference and large-scale training, we build a neural posterior approximator conditioned on both the source and the target sides, and equip it with a reparameterization technique to estimate the variational lower bound.Experiments on both Chinese-English and English-German translation tasks show that the proposed variational neural machine translation achieves significant improvements over the vanilla neural machine translation baselines.

Implicit discourse relation recognition is a crucial component for automatic discourselevel analysis and nature language understanding.Previous studies exploit discriminative models that are built on either powerful manual features or deep discourse representations.In this paper, instead, we explore generative models and propose a variational neural discourse relation recognizer.We refer to this model as VarNDRR.VarNDRR establishes a directed probabilistic model with a latent continuous variable that generates both a discourse and the relation between the two arguments of the discourse.In order to perform efficient inference and learning, we introduce neural discourse relation models to approximate the prior and posterior distributions of the latent variable, and employ these approximated distributions to optimize a reparameterized variational lower bound.This allows VarNDRR to be trained with standard stochastic gradient methods.Experiments on the benchmark data set show that VarNDRR can achieve comparable results against stateof-the-art baselines without using any manual features.

Jinsong Su, Deyi Xiong, Yang Liu, Xianpei Han, Hongyu Lin, Junfeng Yao, Min Zhang. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

Lexical selection is of great importance to statistical machine translation. In this paper, we propose a graph-based frame-work for collective lexical selection. The framework is established on a translation graph that captures not only local associ-ations between source-side content words and their target translations but also target-side global dependencies in terms of relat-edness among target items. We also in-troduce a random walk style algorithm to collectively identify translations of source-side content words that are strongly related in translation graph. We validate the ef-fectiveness of our lexical selection frame-work on Chinese-English translation. Ex-periment results with large-scale training data show that our approach significantly improves lexical selection. 1

Learning semantic representations and tree structures of bilingual phrases is beneficial for statistical machine translation.In this paper, we propose a new neural network model called Bilingual Correspondence Recursive Autoencoder (BCor-rRAE) to model bilingual phrases in translation.We incorporate word alignments into BCorrRAE to allow it freely access bilingual constraints at different levels.BCorrRAE minimizes a joint objective on the combination of a recursive autoencoder reconstruction error, a structural alignment consistency error and a crosslingual reconstruction error so as to not only generate alignment-consistent phrase structures, but also capture different levels of semantic relations within bilingual phrases.In order to examine the effectiveness of BCorrRAE, we incorporate both semantic and structural similarity features built on bilingual phrase representations and tree structures learned by BCorrRAE into a state-of-the-art SMT system.Experiments on NIST Chinese-English test sets show that our model achieves a substantial improvement of up to 1.55 BLEU points over the baseline.

Implicit discourse relation recognition remains a serious challenge due to the absence of discourse connectives.In this paper, we propose a Shallow Convolutional Neural Network (SCNN) for implicit discourse relation recognition, which contains only one hidden layer but is effective in relation recognition.The shallow structure alleviates the overfitting problem, while the convolution and nonlinear operations help preserve the recognition and generalization ability of our model.Experiments on the benchmark data set show that our model achieves comparable and even better performance when comparing against current state-of-the-art systems.

Structured perceptron becomes popular for various NLP tasks such as tagging and parsing.Practical studies on NLP did not pay much attention to its regularization.In this paper, we study three simple but effective task-independent regularization methods: (1) one is to average weights of different trained models to reduce the bias caused by the specific order of the training examples; (2) one is to add penalty term to the loss function;(3) and one is to randomly corrupt the data flow during training which is called dropout in the neural network.Experiments are conducted on three NLP tasks, namely Chinese word segmentation, part-of-speech tagging and dependency parsing.Applying proper regularization methods or their combinations, the error reductions with respect to the averaged perceptron for some of these tasks can be up to 10%.

The pivot language approach for statistical machine translation (SMT) is a good method to break the resource bottleneck for certain language pairs. However, in the implementation of conventional approaches, pivot-side context information is far from fully utilized, resulting in erroneous estimations of translation probabilities. In this study, we propose two topic-aware pivot language approaches to use different levels of pivot-side context. The first method takes advantage of document-level context by assuming that the bridged phrase pairs should be similar in the document-level topic distributions. The second method focuses on the effect of local context. Central to this approach are that the phrase sense can be reflected by local context in the form of probabilistic topics, and that bridged phrase pairs should be compatible in the latent sense distributions. Then, we build an interpolated model bringing the above methods together to further enhance the system performance. Experimental results on French-Spanish and French-German translations using English as the pivot language demonstrate the effectiveness of topic-based context in pivot-based SMT.