Embedding-as-a-Service (EaaS) is an effective and convenient deployment solution for addressing various NLP tasks. Nevertheless, recent research has shown that EaaS is vulnerable to model extraction attacks, which could lead to significant economic losses for model providers. For copyright protection, existing methods inject watermark embeddings into text embeddings and use them to detect copyright infringement. However, current watermarking methods often resist only a subset of attacks and fail to provide comprehensive protection. To this end, we present the region-triggered semantic watermarking framework called RegionMarker, which defines trigger regions within a low-dimensional space and injects watermarks into text embeddings associated with these regions. By utilizing a secret dimensionality reduction matrix to project onto this subspace and randomly selecting trigger regions, RegionMarker makes it difficult for watermark removal attacks to evade detection. Furthermore, by embedding watermarks across the entire trigger region and using the text embedding as the watermark, RegionMarker is resilient to both paraphrasing and dimension-perturbation attacks. Extensive experiments on various datasets show that RegionMarker is effective in resisting different attack methods, thereby protecting the copyright of EaaS.

Zifeng Cheng, Lingyun Qian, Zhiwei Jiang, Cong Wang, Yafeng Yin, Fei Shen, Ao Zhou, Qing Gu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Shufan Yang, Zifeng Cheng, Zhiwei Jiang, Qingfeng Qi, Yafeng Yin, Cong Wang, Ao Zhou, Qing Gu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locating the temporal location of event, as the relevant supervision is unavailable. Existing methods rely on explicit alignment constraints between event locations and captions, which involve complex event proposal procedures during both training and inference. To tackle this problem, we propose a novel implicit location-caption alignment paradigm by complementary masking, which simplifies the complex event proposal and localization process while maintaining effectiveness. Specifically, our model comprises two components: a dual-mode video captioning module and a mask generation module. The dual-mode video captioning module captures global event information and generates descriptive captions, while the mask generation module generates differentiable positive and negative masks for localizing the events. These masks enable the implicit alignment of event locations and captions by ensuring that captions generated from positively and negatively masked videos are complementary, thereby forming a complete video description. In this way, even under weak supervision, the event location and event caption can be aligned implicitly. Extensive experiments on the public datasets demonstrate that our method outperforms existing weakly-supervised methods and achieves competitive results compared to fully-supervised methods.

Zifeng Cheng, Zhonghui Wang, Yuchen Fu, Zhiwei Jiang, Yafeng Yin, Cong Wang, Qing Gu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Yuchen Fu, Zifeng Cheng, Zhiwei Jiang, Zhonghui Wang, Yafeng Yin, Zhengliang Li, Qing Gu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences. Meanwhile, extending the context window in LLMs through post-pretraining is highly resource-intensive.To address this, we introduce LongRecipe, an efficient training strategy for extending the context window of LLMs, including impactful token analysis, position index transformation, and training optimization strategies. It simulates long-sequence inputs while maintaining training efficiency and significantly improves the model’s understanding of long-range dependencies. Experiments on three types of LLMs show that LongRecipe can utilize long sequences while requiring only 30% of the target context window size, and reduces computational training resource over 85% compared to full sequence training. Furthermore, LongRecipe also preserves the original LLM’s capabilities in general tasks. Ultimately, we can extend effective context window of open-source LLMs from 8k to 128k, achieving performance close to GPT-4 with just one day of dedicated training using a single GPU with 80G memory.Our code is released at https://github.com/zhiyuanhubj/LongRecipe.

The success of the text-guided diffusion model has inspired the development and release of numerous powerful diffusion models within the open-source community. These models are typically fine-tuned on various expert datasets, showcasing diverse denoising capabilities. Leveraging multiple high-quality models to produce stronger generation ability is valuable, but has not been extensively studied. Existing methods primarily adopt parameter merging strategies to produce a new static model. However, they overlook the fact that the divergent denoising capabilities of the models may dynamically change across different states, such as when experiencing different prompts, initial noises, denoising steps, and spatial locations. In this paper, we propose a novel ensembling method, Adaptive Feature Aggregation (AFA), which dynamically adjusts the contributions of multiple models at the feature level according to various states (i.e., prompts, initial noises, denoising steps, and spatial locations), thereby keeping the advantages of multiple diffusion models, while suppressing their disadvantages. Specifically, we design a lightweight Spatial-Aware Block-Wise (SABW) feature aggregator that adaptive aggregates the block-wise intermediate features from multiple U-Net denoisers into a unified one. The core idea lies in dynamically producing an individual attention map for each model's features by comprehensively considering various states. It is worth noting that only SABW is trainable with about 50 million parameters, while other models are frozen. Both the quantitative and qualitative experiments demonstrate the effectiveness of our proposed method.

Bug localization, which aims to localize software faults specific to a bug report, is valuable for improving software developers' efficiency. This task is often formulated as an information retrieval problem, where potentially buggy files are retrieved and ranked according to their textual similarity to a target bug report. To address this task, many methods have been proposed, primarily focusing on resolving the semantic gap between natural language in bug reports and programming language in source files. Recently, Large Language Models (LLMs) have demonstrated strong capabilities in seamlessly understanding both natural language and programming language, potentially addressing the semantic gap issue through natural conversation. However, the limited context length of prompt and capability of long-context comprehension in existing LLMs make it impossible to directly load the entire codebase (e.g., thousands of code files) into LLMs' prompts to retrieve buggy code files. In this paper, we explore how to leverage existing LLMs for projectlevel bug localization without requiring additional fine-tuning and propose an LLM-based Bug Localization framework, LLM-BL. Our core idea is to enable LLMs to perform bug localization tasks using listwise ranking instructions and to avoid exceeding the context length limit by compressing the codebase through file filtering and content reduction. Specifically, LLM-BL consists of four modules: report expansion, candidate retrieval, content reduction, and LLM-based bug localization. Among them, the first three modules are used to retrieve potential buggy code files and extract bug-related information from the code files, respectively, while the last module enables the LLM to perform bug localization through listwise file ranking. We select three widely used LLMs (i.e., ChatGPT, Llama 3, CodeLlama) as the base LLMs in our framework and conduct extensive experiments on six public projects with two report types (i.e., Java and Python). Experimental results demonstrate that the two LLMs, ChatGPT and Llama 3, can more effectively understand task intentions and more accurately localize buggy files than CodeLlama. Compared to existing methods, LLM-BL achieves better localization performance without requiring any fine-tuning, in a plug-and-play manner. These results demonstrate that both ChatGPT and Llama 3 are effective zero-shot rankers for bug localization.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable multimodal understanding capabilities in Visual Question Answering (VQA) tasks by integrating visual and textual features. However, under the challenging ten-choice question evaluation paradigm, existing methods still exhibit significant limitations when processing PDF documents with complex layouts and lengthy content. Notably, current mainstream models suffer from a strong bias toward English training data, resulting in suboptimal performance for Japanese and other language scenarios. To address these challenges, this paper proposes a novel Japanese PDF document understanding framework that combines multimodal hierarchical reasoning mechanisms with Colqwen-optimized retrieval methods, while innovatively introducing a semantic verification strategy through sub-question decomposition. Experimental results demonstrate that our framework not only significantly enhances the model's deep semantic parsing capability for complex documents, but also exhibits superior robustness in practical application scenarios.

Social Media Popularity Prediction is a complex multimodal task that requires effective integration of images, text, and structured information. However, current approaches suffer from inadequate visual-textual alignment and fail to capture the inherent cross-content correlations and hierarchical patterns in social media data. To overcome these limitations, we establish a multi-class framework, introducing hierarchical prototypes for structural enhancement and contrastive learning for improved vision-text alignment. Furthermore, we propose a feature-enhanced framework integrating dual-grained prompt learning and cross-modal attention mechanisms, achieving precise multimodal representation through fine-grained category modeling. Experimental results demonstrate state-of-the-art performance on benchmark metrics, establishing new reference standards for multimodal social media analysis.

Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and cost-efficient approach that directly modifies the activations of LLMs during the inference stage, aligning their responses with the desired behaviors and avoiding the high cost of fine-tuning. Existing methods typically indiscriminately intervene to all generations or rely solely on the question to determine intervention, which limits the accurate assessment of the intervention strength. To this end, we propose the **F**lexible **A**ctivation **S**teering with **B**acktracking (**FASB**) framework, which dynamically determines both the necessity and strength of intervention by tracking the internal states of the LLMs during generation, considering both the question and the generated content. Since intervening after detecting a deviation from the desired behavior is often too late, we further propose the backtracking mechanism to correct the deviated tokens and steer the LLMs toward the desired behavior. Extensive experiments on the TruthfulQA dataset and six multiple-choice datasets demonstrate that our method outperforms baselines. Our code will be released at https://github.com/gjw185/FASB.

Recent advances in sign language research have benefited from CNN-based backbones, which are primarily transferred from traditional computer vision tasks (\eg object detection, image recognition). However, these CNN-based backbones usually excel at extracting features like contours and texture, but may struggle with capturing sign-related features. To capture such sign-related features, SignGraph model extracts the cross-region sign features by building the Local Sign Graph (LSG) module and the Temporal Sign Graph (TSG) module. However, we emphasize that although capturing cross-region dependencies can improve sign language performance, it may degrade the representation quality of local regions. To mitigate this, we introduce MixSignGraph, which represents sign sequences as a group of mixed graphs for feature extraction. Specifically, besides the LSG module and TSG module that model the intra-frame and inter-frame cross-regions features, we design a simple yet effective Hierarchical Sign Graph (HSG) module, which enhances local region representations following the extraction of cross-region features, by aggregating the same-region features from different-granularity feature maps of a frame, \ie to boost discriminative local features. In addition, to further improve the performance of gloss-free sign language task, we propose a simple yet counter-intuitive Text-based CTC Pre-training (TCTC) method, which generates pseudo gloss labels from text sequences for model pre-training. Extensive experiments conducted on the current five sign language datasets demonstrate that MixSignGraph surpasses the most current models on multiple sign language tasks across several datasets, without relying on any additional cues. Code and models are available at: \href{https://github.com/gswycf/SignLanguage}{\textcolor{blue}{https://github.com/gswycf/SignLanguage}}.

Sign Language Video Generation (SLVG) seeks to generate identity-preserving sign language videos from spoken language texts. Existing methods primarily rely on the single coarse condition (e.g., skeleton sequences) as the intermediary to bridge the translation model and the video generation model, which limits both the naturalness and expressiveness of the generated videos. To overcome these limitations, we propose SignViP, a novel SLVG framework that incorporate multiple fine-grained conditions for improved generation fidelity. Rather than directly translating error-prone high-dimensional conditions, SignViP adopts a discrete tokenization paradigm to integrate and represent fine-grained conditions (i.e., fine-grained poses and 3D hands). SignViP contains three core components. (1) Sign Video Diffusion Model is jointly trained with a multi-condition encoder to learn continuous embeddings that encapsulate fine-grained motion and appearance. (2) Finite Scalar Quantization (FSQ) Autoencoder is further trained to compress and quantize these embeddings into discrete tokens for compact representation of the conditions. (3) Multi-Condition Token Translator is trained to translate spoken language text to discrete multi-condition tokens. During inference, Multi-Condition Token Translator first translates the spoken language text into discrete multi-condition tokens. These tokens are then decoded to continuous embeddings by FSQ Autoencoder, which are subsequently injected into Sign Video Diffusion Model to guide video generation. Experimental results show that SignViP achieves state-of-the-art performance across metrics, including video quality, temporal coherence, and semantic fidelity. The code is available at https://github.com/umnooob/signvip/.

Zero-Shot Cross-Modal Retrieval (ZS-CMR) aims to perform cross-modal retrieval on data of unseen classes, where a key challenge is how to address the modality-gap and domain-shift problems simultaneously. Existing methods tackle this challenge mainly by embracing a sample-label alignment paradigm, which aligns samples of different modalities but of the same class with the word embedding of their class label. However, these methods only focus on the class-level alignment and overlook the alignment of rich fine-grained semantic information in samples, incurring coarse understanding of sample matching and poor generalization on unseen classes. In this article, we propose a novel Fine-Grained Alignment Network, an end-to-end framework that learns representation with two fine-grained alignment strategies, yielding representation space that can be better generalized to unseen classes. Specifically, we extract two kinds of fine-grained representations, region embedding and label distribution, respectively, from aspects of both feature and label. To optimize the region embedding, we propose a Fine-Grained Contrastive Learning (FGCL) strategy to simultaneously conduct class-level alignment and model the intra-class discrepancy. To optimize the label distribution, we propose a Fine-Grained Label Alignment (FGLA) strategy to align diverse fine-grained semantic information among samples, rather than merely label information. Finally, both region embedding and label distribution are utilized together to perform ZS-CMR at a finer granularity. Experimental results on three widely used datasets demonstrate that our method outperforms the state-of-the-art methods by a large margin. Detailed ablation studies have also been carried out, which provably affirm the advantage of each component we propose. Our code will be available at https://github.com/ShipingGe/FGAN .

Despite the recent success of sign language research, the widely adopted CNN-based backbones are mainly migrated from other computer vision tasks, in which the contours and texture of objects are crucial for identifying objects. They usually treat sign frames as grids and may fail to capture effective cross-region features. In fact, sign language tasks need to focus on the correlation of different regions in one frame and the interaction of different regions among adjacent frames for identifying a sign sequence. In this paper, we propose to represent a sign sequence as graphs and introduce a simple yet effective graph-based sign language processing architecture named SignGraph, to extract crossregion features at the graph level. SignGraph consists of two basic modules: Local Sign Graph (LSG) module for learning the correlation of intra-frame cross-region features in one frame and Temporal Sign Graph (TSG) module for tracking the interaction of inter-frame cross-region features among adjacent frames. With LSG and TSG, we build our model in a multiscale manner to ensure that the representation of nodes can capture cross-region features at different granularities. Extensive experiments on current public sign language datasets demonstrate the superiority of our SignGraph model. Our model achieves very competitive performances with the SOTA model, while not using any extra cues. Code and models are available at: https://github.com/gswycf/SignGraph.

Recent advancements in Automatic Prompt Optimization (APO) for text-to-image generation have streamlined user input while ensuring high-quality image output. However, most APO methods are trained assuming a fixed text-to-image model, which is impractical given the emergence of new models. To address this, we propose a novel task, model-generalized automatic prompt optimization (MGAPO), which trains APO methods on a set of known models to enable generalization to unseen models during testing. MGAPO presents significant challenges. First, we experimentally confirm the suboptimal performance of existing APO methods on unseen models. We then introduce a two-stage prompt optimization method, AP-Adapter. In the first stage, a large language model is used to rewrite the prompts. In the second stage, we propose a novel method to construct an enhanced representation space by leveraging inter-model differences. This space captures the characteristics of multiple domain models, storing them as domain prototypes. These prototypes serve as anchors to adjust prompt representations, enabling generalization to unseen models. The optimized prompt representations are subsequently used to generate conditional representations for controllable image generation. We curate a multi-modal, multi-model dataset that includes multiple diffusion models and their corresponding text-image data, and conduct experiments under a model generalization setting. The experimental results demonstrate the AP-Adapter's ability to enable the automatic prompts to generalize well to previously unseen diffusion models, generating high-quality images.

Short video collection is an easy way for users to consume coherent content on various online short video platforms, such as TikTok, YouTube, Douyin, and WeChat Channel. These collections cover a wide range of content, including online courses, TV series, movies, and cartoons. However, short video creators occasionally publish videos in a disorganized manner due to various reasons, such as revisions, secondary creations, deletions, and reissues, which often result in a poor browsing experience for users. Therefore, accurately reordering videos within a collection based on their content coherence is a vital task that can enhance user experience and presents an intriguing research problem in the field of video narrative reasoning. In this work, we curate a dedicated multimodal dataset for this Short Video Ordering (SVO) task and present the performance of some benchmark methods on the dataset. In addition, we further propose an advanced SVO framework with the aid of position decoding and successor prediction. The proposed framework combines both pairwise and listwise ordering paradigms, which can get rid of the issues from both quadratic growth and cascading conflict in the pairwise paradigm, and improve the performance of existing listwise methods. Extensive experiments demonstrate that our method achieves the best performance on our open SVO dataset, and each component of the framework contributes to the final performance. Both the SVO dataset and code will be released at https://github.com/ShipingGe/SVO.

Few-shot sequence labeling aims to identify novel classes based on only a few labeled samples. Existing methods solve the data scarcity problem mainly by designing token-level or span-level labeling models based on metric learning. However, these methods are only trained at a single granularity (i.e., either token-level or span-level) and have some weaknesses of the corresponding granularity. In this article, we first unify token- and span-level supervisions and propose a Consistent Dual Adaptive Prototypical (CDAP) network for few-shot sequence labeling. CDAP contains the token- and span-level networks, jointly trained at different granularities. To align the outputs of two networks, we further propose a consistent loss to enable them to learn from each other. During the inference phase, we propose a consistent greedy inference algorithm that first adjusts the predicted probability and then greedily selects non-overlapping spans with maximum probability. Extensive experiments show that our model achieves new state-of-the-art results on three benchmark datasets. All the code and data of this work will be released at https://github.com/zifengcheng/CDAP .

For deep ordinal classification, learning a well-structured feature space specific to ordinal classification is helpful to properly capture the ordinal nature among classes. Intuitively, when Euclidean distance metric is used, an ideal ordinal layout in feature space would be that the sample clusters are arranged in class order along a straight line in space. However, enforcing samples to conform to a specific layout in the feature space is a challenging problem. To address this problem, in this paper, we propose a novel Constrained Proxies Learning (CPL) method, which can learn a proxy for each ordinal class and then adjusts the global layout of classes by constraining these proxies. Specifically, we propose two kinds of strategies: hard layout constraint and soft layout constraint. The hard layout constraint is realized by directly controlling the generation of proxies to force them to be placed in a strict linear layout or semicircular layout (i.e., two instantiations of strict ordinal layout). The soft layout constraint is realized by constraining that the proxy layout should always produce unimodal proxy-to-proxies similarity distribution for each proxy (i.e., to be a relaxed ordinal layout). Experiments show that the proposed CPL method outperforms previous deep ordinal classification methods under the same setting of feature extractor.

Automated Essay Scoring (AES) aims to score essays written in response to specific prompts.Many AES models have been proposed, but most of them are either prompt-specific or prompt-adaptive and cannot generalize well on "unseen" prompts.This work focuses on improving the generalization ability of AES models from the perspective of domain generalization, where the data of target prompts cannot be accessed during training.Specifically, we propose a prompt-aware neural AES model to extract comprehensive representation for essay scoring, including both promptinvariant and prompt-specific features.To improve the generalization of representation, we further propose a novel disentangled representation learning framework.In this framework, a contrastive norm-angular alignment strategy and a counterfactual self-training strategy are designed to disentangle the prompt-invariant information and prompt-specific information in representation.Extensive experimental results on datasets of both ASAP and TOEFL11 demonstrate the effectiveness of our method under the domain generalization setting.

Automated Essay Scoring (AES) aims to evaluate the quality score for input essays.In this work, we propose a novel unsupervised AES approach ULRA, which does not require groundtruth scores of essays for training.The core idea of our ULRA is to use multiple heuristic quality signals as the pseudo-groundtruth, and then train a neural AES model by learning from the aggregation of these quality signals.To aggregate these inconsistent quality signals into a unified supervision, we view the AES task as a ranking problem, and design a special Deep Pairwise Rank Aggregation (DPRA) loss for training.In the DPRA loss, we set a learnable confidence weight for each signal to address the conflicts among signals, and train the neural AES model in a pairwise way to disentangle the cascade effect among partialorder pairs.Experiments on eight prompts of ASPA dataset show that ULRA achieves the state-of-the-art performance compared with previous unsupervised methods in terms of both transductive and inductive settings.Further, our approach achieves comparable performance with many existing domain-adapted supervised models, showing the effectiveness of ULRA.The code is available at https: //github.com/tenvence/ulra.

There are two problems that widely exist in current end-to-end sign language processing architecture. One is the CTC spike phenomenon which weakens the visual representational ability in Continuous Sign Language Recognition (CSLR). The other one is the exposure bias problem which leads to the accumulation of translation errors during inference in Sign Language Translation (SLT). In this paper, we tackle these issues by introducing contrast learning, aiming to enhance both visual-level feature representation and semantic-level error tolerance. Specifically, to alleviate CTC spike phenomenon and enhance visual-level representation, we design a visual contrastive loss by minimizing visual feature distance between different augmented samples of frames in one sign video, so that the model can further explore features by utilizing numerous unlabeled frames in an unsupervised way. To alleviate exposure bias problem and improve semantic-level error tolerance, we design a semantic contrastive loss by re-inputting the predicted sentence into semantic module and comparing features of ground-truth sequence and predicted sequence, for exposing model to its own mistakes. Besides, we propose two new metrics, i.e., Blank Rate and Consecutive Wrong Word Rate to directly reflect our improvement on the two problems. Extensive experimental results on current sign language datasets demonstrate the effectiveness of our approach, which achieves state-of-the-art performance.

To provide instant communication for hearing-impaired people, it is essential to achieve real-time sign language processing anytime anywhere. Therefore, in this paper, we propose a Region-aware Temporal Graph based neural Network (RTG-Net), aiming to achieve real-time Sign Language Recognition (SLR) and Translation (SLT) on edge devices. To reduce the computation overhead, we first construct a shallow graph convolution network to reduce model size by decreasing model depth. Besides, we apply structural re-parameterization to fuse the convolutional layer, batch normalization layer and all branches to simplify model complexity by reducing model width. To achieve the high performance in sign language processing as well, we extract key regions based on keypoints in skeleton from each frame, and design a region-aware temporal graph to combine key regions and full frame for feature representation. In RTG-Net, we design a multi-stage training strategy to optimize keypoint selection, SLR and SLT step by step. Experimental results demonstrate that RTG-Net achieves comparable performance with existing methods in SLR or SLT, while greatly reducing the computation overhead and achieving real-time sign language processing on edge devices. Our code is available at https://github.com/SignLanguageCode/realtimeSLRT.

Audio-Visual Event Localization (AVEL) aims to locate events that are both visible and audible in a video. Existing AVEL methods primarily focus on learning generic localization patterns that are applicable to all events. However, events often exhibit modality biases, such as visual-dominated, audio-dominated, or modality-balanced, which can lead to different localization preferences. These preferences may be overlooked by existing methods, resulting in unsatisfactory localization performance. To address this issue, this paper proposes a novel event-aware localization paradigm, which first identifies the event category and then leverages localization preferences specific to that event for improved event localization. To achieve this, we introduce a memory-assisted metric learning framework, which utilizes historic segments as anchors to adjust the unified representation space for both event classification and event localization. To provide sufficient information for this metric learning, we design a spatial-temporal audio-visual fusion encoder to capture the spatial and temporal interaction between audio and visual modalities. Extensive experiments on the public AVE dataset in both fully-supervised and weakly-supervised settings demonstrate the effectiveness of our approach. Code will be released at https://github.com/ShipingGe/AVEL.

Unsupervised readability assessment aims to evaluate the reading difficulty of text without any manually-labeled data for model training. This is a challenging task because the absence of labeled data makes it difficult for the model to understand what readability is. In this paper, we propose a novel framework to Learn a neural model from Weak Readability Signals (LWRS). Instead of relying on labeled data, LWRS utilizes a set of heuristic signals that specialize in describing text readability from different aspects to guide the model in outputting readability scores for ranking. Specifically, to effectively use multiple heuristic weak signals for model training, we build a multi-signal learning model that ranks the unlabeled texts from multiple readability-related aspects based on intra- and inter-signal learning. We also adopt the pairwise ranking paradigm to reduce the cascade coupling among partial-order pairs. Furthermore, we propose identifying the most representative signal based on the batch-level consensus distribution of all signals. This strategy helps identify the predicted signal that is most correlated with readability in the absence of ground-truth labels. We conduct experiments on three public readability assessment datasets. The experimental results demonstrate that our LWRS outperforms each heuristic signal and their combinations significantly, and can even perform comparably with some supervised methods. Additionally, our LWRS trained on one dataset can be effectively transferred to other datasets, including those in other languages, which indicates its good generalization and potential for wide application.

Recognizing emotions from multi-modal data is an emotion recognition task that requires strong multi-modal representation ability. The general approach to this task is to naturally train the representation model on training data without intervention. However, such natural training scheme is prone to modality bias of representation (i.e., tending to over-encode some informative modalities while neglecting other modalities) and data bias of training (i.e., tending to overfit training data). These biases may lead to instability (e.g., performing poorly when the neglected modality is dominant for recognition) and weak generalization (e.g., performing poorly when unseen data is inconsistent with overfitted data) of the model on unseen data. To address these problems, this paper presents two adversarial training strategies to learn more robust multi-modal representation for multi-label emotion recognition. Firstly, we propose an adversarial temporal masking strategy, which can enhance the encoding of other modalities by masking the most emotion-related temporal units (e.g., words for text or frames for video) of the informative modality. Secondly, we propose an adversarial parameter perturbation strategy, which can enhance the generalization of the model by adding the adversarial perturbation to the parameters of model. Both strategies boost model performance on the benchmark MMER datasets CMU-MOSEI and NEMu. Experimental results demonstrate the effectiveness of the proposed method compared with the previous state-of-the-art method. Code will be released at https://github.com/ShipingGe/MMER.

Emotion-cause pair extraction (ECPE) is a recently proposed task that aims to extract the potential clause pairs of emotions and its corresponding causes in a document. In this article, we propose a new paradigm for the ECPE task. We cast the task as a two-turn machine reading comprehension (MRC) task, i.e., the extraction of emotions and causes is transformed to the task of identifying answer clauses from the input document specific to a query. This two-turn MRC formalization brings several key advantages: First, the QA manner provides an explicit pairing way to identify causes specific to the target emotion; second, it provides a natural way of jointly modeling the emotion extraction, the cause extraction, and the pairing of emotion and cause; and third, it allows us to exploit the well-developed MRC models. Based on the two-turn MRC formalization, we propose a dual-MRC framework to extract emotion-cause pairs in a dual-direction way, which enables a more comprehensive coverage of all pairing cases. Furthermore, we propose a consistent training strategy for the second-turn query, so the model is able to filter the errors produced by the first turn at inference. Experiments on two benchmark datasets demonstrate that our method outperforms previous methods and achieves state-of-the-art performance. All the code and data of this work can be obtained at https://github.com/zifengcheng/CD-MRC .

Open intent classification is a practical yet challenging task in dialogue systems. Its objective is to accurately classify samples of known intents while at the same time detecting those of open (unknown) intents. Existing methods usually use outlier detection algorithms combined with K-class classifier to detect open intents, where K represents the class number of known intents. Different from them, in this paper, we consider another way without using outlier detection algorithms. Specifically, we directly train a (K+1)-class classifier for open intent classification, where the (K+1)-th class represents open intents. To address the challenge that training a (K+1)-class classifier with training samples of only K classes, we propose a deep model based on Soft Labeling and Manifold Mixup (SLMM). In our method, soft labeling is used to reshape the label distribution of the known intent samples, aiming at reducing model’s overconfident on known intents. Manifold mixup is used to generate pseudo samples for open intents, aiming at well optimizing the decision boundary of open intents. Experiments on four benchmark datasets demonstrate that our method outperforms previous methods and achieves state-of-the-art performance. All the code and data of this work can be obtained at.1

As an essential communication way for deaf-mutes, sign languages are expressed by human actions. To distinguish human actions for sign language understanding, the skeleton which contains position information of human pose can provide an important cue, since different actions usually correspond to different poses/skeletons. However, skeleton has not been fully studied for Sign Language Translation (SLT), especially for end-to-end SLT. Therefore, in this paper, we propose a novel end-to-end Skeleton-Aware neural Network (SANet) for video-based SLT. Specifically, to achieve end-to-end SLT, we design a self-contained branch for skeleton extraction. To efficiently guide the feature extraction from video with skeletons, we concatenate the skeleton channel and RGB channels of each frame for feature extraction. To distinguish the importance of clips, we construct a skeleton-based Graph Convolutional Network (GCN) for feature scaling, i.e., giving importance weight for each clip. The scaled features of each clip are then sent to a decoder module to generate spoken language. In our SANet, a joint training strategy is designed to optimize skeleton extraction and sign language translation jointly. Experimental results on two large scale SLT datasets demonstrate the effectiveness of our approach, which outperforms the state-of-the-art methods. Our code is available at https://github.com/SignLanguageCode/SANet.

One-shot automated essay scoring (AES) aims to assign scores to a set of essays written specific to a certain prompt, with only one manually scored essay per distinct score. Compared to the previous-studied prompt-specific AES which usually requires a large number of manually scored essays for model training (e.g., about 600 manually scored essays out of totally 1000 essays), one-shot AES can greatly reduce the workload of manual scoring. In this paper, we propose a Transductive Graph-based Ordinal Distillation (TGOD) framework to tackle the task of one-shot AES. Specifically, we design a transductive graph-based model as a teacher model to generate pseudo labels of unlabeled essays based on the one-shot labeled essays. Then, we distill the knowledge in the teacher model into a neural student model by learning from the high confidence pseudo labels. Different from the general knowledge distillation, we propose an ordinal-aware unimodal distillation which makes a unimodal distribution constraint on the output of student model, to tolerate the minor errors existed in pseudo labels. Experimental results on the public dataset ASAP show that TGOD can improve the performance of existing neural AES models under the one-shot AES setting and achieve an acceptable average QWK of 0.69.

Emotion-cause pair extraction is a recently proposed task that aims at extracting all potential clause-level pairs of emotion and cause in text. To solve this task, researchers first proposed a two-step pipeline method. This method extracts the emotions and causes individually in the first step, then pairs the extracted emotions and causes and filters the invalid emotion-cause pairs in the second step. Due to that the two-step method has the error accumulation problem and is hard to be optimized jointly, several one-step end-to-end models have been proposed. These models share a similar underlying idea, that is, reframing the emotion-cause pair extraction task as a classification problem of candidate clause pairs. Unlike these models, in this paper, we reframe the emotion-cause pair extraction task as a unified sequence labeling problem, which allows to extract emotion-cause pairs through one pass of sequence labeling. This is realized by designing a special set of unified labels. In the unified label, we design a content part for emotion/cause identification and a pairing part for clause pairing. Then the emotion-cause pairs can be implicitly derived from the unified labels. To address this unified sequence labeling problem, we propose a unified target-oriented sequence-to-sequence model, which comprehensively utilizes the information of target clause, global context, and former decoded label, to perform end-to-end unified sequence labeling. The experimental results demonstrate the effectiveness of both our proposed unified sequence labeling scheme and unified target-oriented sequence-to-sequence model. All the code and data of this work can be obtained at https://github.com/zifengcheng/UTOS.

Emotion-cause pair extraction (ECPE) is a new task which aims at extracting the potential clause pairs of emotions and corresponding causes in a document.To tackle this task, a two-step method was proposed by previous study which first extracted emotion clauses and cause clauses individually, then paired the emotion and cause clauses, and filtered out the pairs without causality.Different from this method that separated the detection and the matching of emotion and cause into two steps, we propose a Symmetric Local Search Network (SLSN) model to perform the detection and matching simultaneously by local search.SLSN consists of two symmetric subnetworks, namely the emotion subnetwork and the cause subnetwork.Each subnetwork is composed of a clause representation learner and a local pair searcher.The local pair searcher is a specially-designed cross-subnetwork component which can extract the local emotion-cause pairs.Experimental results on the ECPE corpus demonstrate the superiority of our SLSN over existing state-of-the-art methods.

Existing methods for readability assessment usually construct inductive classification models to assess the readability of singular text documents based on extracted features, which have been demonstrated to be effective. However, they rarely make use of the interrelationship among documents on readability, which can help increase the accuracy of readability assessment. In this article, we adopt a graph‐based classification method to model and utilize the relationship among documents using the coupled bag‐of‐words model. We propose a word coupling method to build the coupled bag‐of‐words model by estimating the correlation between words on reading difficulty. In addition, we propose a two‐view graph propagation method to make use of both the coupled bag‐of‐words model and the linguistic features. Our method employs a graph merging operation to combine graphs built according to different views, and improves the label propagation by incorporating the ordinal relation among reading levels. Experiments were conducted on both English and Chinese data sets, and the results demonstrate both effectiveness and potential of the method.

In this paper, we present a method which learns the word embedding for readability assessment. For the existing word embedding models, they typically focus on the syntactic or semantic relations of words, while ignoring the reading difficulty, thus they may not be suitable for readability assessment. Hence, we provide the knowledge-enriched word embedding (KEWE), which encodes the knowledge on reading difficulty into the representation of words. Specifically, we extract the knowledge on word-level difficulty from three perspectives to construct a knowledge graph, and develop two word embedding models to incorporate the difficulty context derived from the knowledge graph to define the loss functions. Experiments are designed to apply KEWE for readability assessment on both English and Chinese datasets, and the results demonstrate both effectiveness and potential of KEWE.

This paper proposes a graph-based readability assessment method using word coupling.Compared to the state-of-theart methods such as the readability formulae, the word-based and feature-based methods, our method develops a coupled bag-of-words model which combines the merits of word frequencies and text features.Unlike the general bag-of-words model which assumes words are independent, our model correlates the words based on their similarities on readability.By applying TF-IDF (Term Frequency and Inverse Document Frequency), the coupled TF-IDF matrix is built, and used in the graph-based classification framework, which involves graph building, merging and label propagation.Experiments are conducted on both English and Chinese datasets.The results demonstrate both effectiveness and potential of the method.

In recent years, researchers have paid more attention to influence maximization problem. This problem is firstly defined by Domingos and Richardson as follows: finding a small set of individuals in a social network that could maximize the spread of influence under certain influence cascade model. To solve this issue, researchers proposed different algorithms. However, in all of these algorithms, the size of the chosen individuals -k, is assigned in advance. In this paper, we conduct a preliminary exploration on the relationship between the size of the chosen set and the corresponding influence spread. We propose two metrics to analyze the factor k. Then we further consider the performance metric of the chosen set, which can be described by the stability of the chosen set. Experimental results on two real social networks show the efficiency and necessity of our proposed metrics.