Zhuoyue Gao, Xiaohui Wang, Xiaocui Yang, Wen Zhang, Daling Wang, Shi Feng, Yifei Zhang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

YiJie Huang, Xiaocui Yang, Shi Feng, Wen Zhang, Kaisong Song, Yifei Zhang, Daling Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

YongKang Liu, Xingle Xu, Ercong Nie, Zijing Wang, Shi Feng, Daling Wang, Qian Li, Hinrich Schuetze. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

YongKang Liu, Jiayang Yu, Mingyang Wang, Yiqun Zhang, Ercong Nie, Shi Feng, Daling Wang, Kaisong Song, Hinrich Schuetze. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Peidong Wang, Zhiming Ma, Xin Dai, YongKang Liu, Shi Feng, Xiaocui Yang, Wenxing Hu, Zhihao Wang, Mingjun Pan, Li Yuan, Daling Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Ming Wang, Shuang Wu, Bixuan Wang, Lu Lin, Yuxin Chen, Xiaocui Yang, Daling Wang, Shi Feng, Yifei Zhang, Yufan Sun. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zijing Wang, Xingle Xu, YongKang Liu, Yiqun Zhang, Peiqin Lin, Shi Feng, Daling Wang, Xiaocui Yang, Hinrich Schuetze. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zili Wei, Yilin Wang, Xiaocui Yang, Shi Feng, Weidong Bao, Daling Wang, Zihan Wang, Yifei Zhang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Yiqun Zhang, Hao Li, Zihan Wang, Shi Feng, Xiaocui Yang, Daling Wang, Bo Zhang, Lei Bai, Shuyue Hu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

To address the interpretability challenge in machine learning (ML) systems, counterfactual explanations (CEs) have emerged as a promising solution. CEs are unique as they provide workable suggestions to users, instead of explaining why a certain outcome was predicted. The application of CEs encounters two main challenges: general user preferences and variable ML systems. On one hand, user preferences for specific values can vary depending on the task and scenario. On the other hand, the ML systems for verification may change while the CEs are performed. Thus, user preferences tend to be general rather than specific, and CEs need to be adaptable to variable ML models while maintaining robustness even as these models change. Facing these challenges, we propose general user preferences based on insights from psychology and behavioral science, and add the challenge of non-static ML systems as one preference. Moreover, we introduce a novel method, Tree-based Conditions Optional Links (T-COL) for generating CEs adaptable to general user preferences. Moreover, we employ T-COL to enhance the robustness of CEs with specific conditions, making CEs robust even when the ML models are replaced. To assess subjectivity preferences, we define LLM-based autonomous agents to simulate users and align them with real users. Experiments show that T-COL outperforms all baselines in adapting to general user preferences.

Dexian Cai, Xiaocui Yang, YongKang Liu, Daling Wang, Shi Feng, Yifei Zhang, Soujanya Poria. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang, Shi Feng, Daling Wang, Linhao Yu, Xingguang Ji, Yu Tian, V. W., Fuzheng Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Empathetic conversation is a crucial characteristic in daily conversations between individuals. Nowadays, Large Language models (LLMs) have shown outstanding performance in generating empathetic responses. Knowledge bases like COMET can assist LLMs in mitigating illusions and enhancing the understanding of users’ intentions and emotions. However, models remain heavily reliant on fixed knowledge bases and unrestricted incorporation of external knowledge can introduce noise. Tool learning is a flexible end-to-end approach that assists LLMs in handling complex problems. In this paper, we propose Emotional Knowledge Tool Calling (EKTC) framework, which encapsulates the commonsense knowledge bases as empathetic tools, enabling LLMs to integrate external knowledge flexibly through tool calling. In order to adapt the models to the new task, we construct a novel dataset TOOL-ED based on the EMPATHETICDIALOGUE (ED) dataset. We validate EKTC on the ED dataset, and the experimental results demonstrate that our framework can enhance the ability of LLMs to generate empathetic responses effectively. Our code is available at https://anonymous.4open.science/r/EKTC-3FEF.

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their further evolution is often hampered by the scarcity of high-quality training data and the heavy reliance of traditional methods on expert-labeled data.This reliance sets a ceiling on LLM performance and is particularly challenging in low data resource scenarios where extensive supervision is unavailable.To address this issue, we propose a novel paradigm named LANCE (LANguage models as Continuous self-Evolving data engineers) that enables LLMs to train themselves by autonomously generating, cleaning, reviewing, and annotating data with preference information.Our approach demonstrates that LLMs can serve as continuous self-evolving data engineers, significantly reducing the time and cost of post-training data construction.Through iterative fine-tuning on Qwen2 series models, we validate the effectiveness of LANCE across various tasks, showing that it can maintain high-quality data generation and continuously improve model performance.Across multiple benchmark dimensions, LANCE results in an average score enhancement of 3.64 for Qwen2-7B and 1.75 for Qwen2-7B-Instruct.This autonomous data construction paradigm not only lessens reliance on human experts or external models but also ensures data aligns with human preferences, offering a scalable path for LLM self-improvement, especially in contexts with limited supervisory data.

Multimodal conversation, a crucial form of human communication, carries rich emotional content, making the exploration of the causes of emotions within it a research endeavor of significant importance. However, existing research on the causes of emotions typically employs an utterance selection method within a single textual modality to locate causal utterances. This approach remains limited to coarse-grained assessments, lacks nuanced explanations of emotional causation, and demonstrates inadequate capability in identifying multimodal emotional triggers. Therefore, we introduce a task-Multimodal Emotion Cause Explanation in Conversation (MECEC). This task aims to generate a summary based on the multimodal context of conversations, clearly and intuitively describing the reasons that trigger a given emotion. To adapt to this task, we develop a new dataset (ECEM) based on the MELD dataset. ECEM combines video clips with detailed explanations of character emotions, helping to explore the causal factors behind emotional expression in multimodal conversations. A novel approach, FAME-Net, is further proposed, that harnesses the power of Large Language Models (LLMs) to analyze visual data and accurately interpret the emotions conveyed through facial expressions in videos. By exploiting the contagion effect of facial emotions, FAME-Net effectively captures the emotional causes of individuals engaged in conversations. Our experimental results on the newly constructed dataset show that FAME-Net outperforms several excellent baselines. Code and dataset are available at https://github.com/3222345200/FAME-Net.

In recent years, Multimodal Sentiment Analysis (MSA) has attracted growing attention for its ability to interpret human emotions by integrating information across multiple modalities. Multimodal Conversational Aspect-based Sentiment Analysis (MCABSA) extends this research frontier by incorporating multi-party conversational contexts and requiring comprehensive extraction of sentiment elements. MCABSA presents substantial challenges, including the need to understand complex conversational contexts, integrate heterogeneous multimodal signals, and identify causal reasoning at the cognitive level. To address these challenges, we propose a two-stage Full Fine-tuning and LLM Post-processing (FLP) framework. In the first stage, we develop a multimodal caption-enhanced full fine-tuning pipeline that performs structured extraction of sextuples and sentiment flip tuples. The second stage introduces paraphrase-based sextuple verification to identify and filter low-quality sextuples for Panoptic Sentiment Sextuple Extraction (Task-1), while implementing trigger classification with a distribution alignment mechanism to determine trigger types for sentiment flipping and enhance output consistency for Sentiment Flipping Analysis (Task-2). Comprehensive experiments on both MCABSA challenge subtasks demonstrate the effectiveness of our approach, achieving 1st place on Task-1 and 3rd place on Task-2.

Sentiment Triplet Extraction (STE) is a challenging Aspect-based Sentiment Analysis task that involves identifying aspect terms, aspect categories, opinion terms, and their corresponding sentiment polarities in sentences. However, the complex relationships and implicit elements constituting sentiment triplets (aspect, opinion, polarity) or (aspect, category, polarity) pose a significant challenge. This paper proposes a novel model called Multi-view Contrastive Learning (MCL) for STE. We treat STE as a text generation task and employ Contrastive Learning at both the triplet and sentiment views. At the triplet view, the source text is used as an anchor, and the target text is regarded as positive samples, while negative samples are obtained by destroying triplet elements in the target text. At the sentiment view, aspect terms are concatenated with their corresponding opinion terms or categories, and the same sentiment polarity in the dataset is used as positive samples, while different polarities are considered negative samples. Our experimental results show that the proposed model outperforms the baseline GAS-EXTRACTION by a significant margin, with every improvement on F1 of 5.21 for Aspect Sentiment Triplet Extraction and 2.98 for Aspect Category Sentiment Detection. These results highlight the effectiveness of incorporating Contrastive Learning in the STE task.

Yiqun Zhang, Fanheng Kong, Peidong Wang, Shuang Sun, SWangLing SWangLing, Shi Feng, Daling Wang, Yifei Zhang, Kaisong Song. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Empathetic response generation aims to understand the user’s feelings emotionally and generate responses with appropriate emotion. According to psychological theories, empathy consists of two main aspects: affection and cognition. However, existing works lack the perception of fine-grained dialogue emotion propagation, as well as have limitations in reasoning about the intentions of users on cognition, which affect the quality of empathetic response. To this end, we propose to generate Empathetic response based on in-context Commonsense reasoning and Reinforcement Learning (EmpCRL). First, we use a current popular large language model combined with multi-view contextual reasoning to broaden the cognitive boundaries through in-context learning. Furthermore, we infer the response emotion by jointly modeling the dialogue history and emotion flow, and achieve the control of response emotion and diversity through reinforcement learning. Extensive experiments on EmpatheticDialogues dataset show that our model outperforms state-of-the-art models in both automatic and human evaluation.

Role-oriented dialogue summarization aims at generating summaries for different roles in dialogue, e.g., user and agent. Interaction between different roles is vital for the task. Existing methods could not fully capture interaction patterns between roles when encoding dialogue, thus are prone to ignore the interaction-related key information. In this paper, we propose a contrastive learning based interaction-aware model for the role-oriented dialogue summarization namely CIAM. An interaction-aware contrastive objective is constructed to guide the encoded dialogue representation to learn role-level interaction. The representation is then used by the decoder to generate role-oriented summaries. The contrastive objective is trained jointly with the primary dialogue summarization task. Additionally, we innovatively utilize different decoder start tokens to control what kind of summary to generate, thus could generate different role-oriented summaries with a unified model. Experimental results show that our method achieves new state-of-the-art results on two public datasets. Extensive analyses further demonstrate that our method excels at capturing interaction information between different roles and producing informative summaries.

Responding with multimodal content has been recognized as one of the essential functionalities of intelligent conversational agents. However, existing research on multimodal dialogues primarily focuses on two topics: (1) textual response generation that ground the conversation on a given image; and (2) visual response selection based on the dialogue context. In light of the aforementioned gap, we propose mulTImodal GEnerator for dialogue Response (TIGER), a unified generative model framework for multimodal dialogue response generation. Through extensive experiments, TIGER has demonstrated new state-of-the-art results, providing users with an enhanced conversational experience. A multimodal dialogue system based on TIGER is available at https://github.com/friedrichor/TIGER. A video demonstrating the system is available at https://www.youtube.com/watch?v=Kd0CMwDs8Rk.

Recently, we have witnessed a significant performance boosting for dialogue response selection task achieved by Cross-Encoder based models. However, such models directly feed the concatenation of context and response into the pre-trained model for interactive inference, ignoring the comprehensively independent representation modeling of context and response. Moreover, randomly sampling negative responses from other dialogue contexts is simplistic, and the learned models have poor generalization capability in realistic scenarios. In this paper, we propose a response selection model called BERT-BC that combines the representation-based Bi-Encoder and interaction-based Cross-Encoder. Three contrastive learning methods are devised for the Bi-Encoder to align context and response to obtain the better semantic representation. Meanwhile, according to the alignment difficulty of context and response semantics, the harder samples are dynamically selected from the same batch with negligible cost and sent to Cross-Encoder to enhance the model’s interactive reasoning ability. Experimental results show that BERT-BC can achieve state-of-the-art performance on three benchmark datasets for multi-turn response selection.

Although large language models(LLMs) show amazing capabilities, among various exciting applications discovered for LLMs fall short in other low-resource languages. Besides, most existing methods depend on large-scale dialogue corpora and thus building systems for dialogue generation in a zero-shot scenario remains a considerable challenge. To address this challenge, we propose a novel end-to-end zero-shot dialogue generation model ChatZero based on cross-lingual code-switching method. First, we construct code-switching language and pseudo-target language with placeholders. Then for cross-lingual semantic transfer, we employ unsupervised contrastive learning to minimize the semantics gap of the source language, code-switching language, and pseudo-target language that are mutually positive examples in the high dimensional semantic space. Experiments on the multilingual DailyDialog and DSTC7-AVSD datasets demonstrate that ChatZero can achieve more than 90% of the original performance under the zero-shot case compared to supervised learning, and achieve state-of-the-art performance compared with other baselines.

Full-parameter fine-tuning (FPFT) has become the go-to choice for adapting language models (LMs) to downstream tasks due to its excellent performance.As LMs grow in size, fine-tuning the full parameters of LMs requires a prohibitively large amount of GPU memory.Existing approaches utilize zeroth-order optimizer to conserve GPU memory, which potentially compromises the performance of LMs as non-zero order optimizers tend to converge more readily on most downstream tasks.We propose a novel, memory-efficient, optimizer-independent, end-to-end hierarchical fine-tuning strategy, HiFT, which only updates a subset of parameters at each training step.HiFT significantly reduces the amount of gradients and optimizer state parameters residing in GPU memory at the same time, thereby reducing GPU memory usage.Our results demonstrate that: (1) HiFT achieves comparable performance with parameter-efficient fine-tuning and standard FPFT.(2) Results on six models show that HiFT reduces the number of trainable parameters by about 89.18% on average compared to FPFT.(3) HiFT supports FPFT of 7B models for 24G GPU memory devices under mixed precision without using any memory saving techniques.(4) HiFT supports various optimizers including AdamW, AdaGrad, SGD, etc.The source code link is https://github.com/misonsky/HiFT.

Empathy is a key factor in human emotional communication and social interaction. Personality is closely related to empathy, which is shaped by the interaction of cognition and affection, and plays a crucial role in emotional expression. However, previous studies have neglected personality as an important empathetic factor. In this work, we propose a dynamic Personality Extraction and Contextual Emotional Reasoning (PECER) model for empathetic dialogue generation. We constructed a contextual emotional reasoner that predicts emotional reactions based on dialogue history. Then we use a personality extractor to dynamically extract the speaker’s personality. Furthermore, a fusion mechanism is designed to inject dialogue history, personality and emotional reactions into the empathetic response generation process. Experimental results show that PECER outperforms state-of-the-art baselines in both automatic and human evaluation.

We investigate response generation for multiturn dialogue in generative chatbots.Existing generative models based on RNNs (Recurrent Neural Networks) usually employ the last hidden state to summarize the history, which makes models unable to capture the subtle variability observed in different dialogues and cannot distinguish the differences between dialogues that are similar in composition.In this paper, we propose Pseudo-Variational Gated Recurrent Unit (PVGRU).The key novelty of PVGRU is a recurrent summarizing variable that aggregates the accumulated distribution variations of subsequences.We train PVGRU without relying on posterior knowledge, thus avoiding the training-inference inconsistency problem.PVGRU can perceive subtle semantic variability through summarizing variables that are optimized by two objectives we employ for training: distribution consistency and reconstruction.In addition, we build a Pseudo-Variational Hierarchical Dialogue (PVHD) model based on PVGRU.Experimental results demonstrate that PVGRU can broadly improve the diversity and relevance of responses on two benchmark datasets.

Dialogue-based automatic disease diagnosis has the potential to assist medical professionals in enhancing the accuracy and efficiency of diagnosis and treatment. Nonetheless, prior models grounded in reinforcement learning often exhibit a tendency to inquire about unrelated symptoms that hold limited relevance to the available symptom information within the constrained number of conversational exchanges. Consequently, these models may hastily assign a diagnosis to the patient. To address this issue, our paper draws inspiration from the diagnostic procedures employed by real-world physicians and introduces a novel two-stage training strategy termed TS-DDD for Dialogue-based Disease Diagnosis. In the initial stage, we pretrain two classifiers for symptom inquiry and disease prediction, separately. In the second stage, we devise a joint training framework that seamlessly integrates symptom inquiry, disease prediction, and decision-making processes. Extensive experiments are conducted and the results validate the effectiveness of our proposed TS-DDD model.

Multimodal sentiment analysis has received extensive attention with the explosion of multimodal data. For multimodal data, representations should have disparate distributions in the feature space under different labels. The paired multi-modal image-text posts should be closer than unpaired. We propose Multimodal fine-grained interaction with the Multiple Contrastive Learning (M2CL) model for image-text multi-modal sentiment detection. Specifically, we first obtain the reinforced global representation of one modality with the assistance of fine-grained information from another via the Multimodal Interaction Component. Then, we introduce the Multiple Contrastive Learning Component, including Supervised Contrastive Learning (SCL) and Dual Multimodal Contrastive Learning (DMCL). SCL accomplishes pushing the posts with the same sentiment closer and pulling the instances of different sentiments apart within each modality. DMCL pushes the paired image-text features together and pulls the unpaired apart with multiple stages. Extensive experiments conducted on three datasets confirm the effectiveness of our approach.

Multimodal sentiment analysis has gained significant attention due to the proliferation of multimodal content on social media. However, existing studies in this area rely heavily on large-scale supervised data, which is time-consuming and labor-intensive to collect. Thus, there is a need to address the challenge of few-shot multimodal sentiment analysis. To tackle this problem, we propose a novel method called Multimodal Probabilistic Fusion Prompts (MultiPoint) that leverages diverse cues from different modalities for multimodal sentiment detection in the few-shot scenario. Specifically, we start by introducing a Consistently Distributed Sampling approach called CDS, which ensures that the few-shot dataset has the same category distribution as the full dataset. Unlike previous approaches primarily using prompts based on the text modality, we design unified multimodal prompts to reduce discrepancies between different modalities and dynamically incorporate multimodal demonstrations into the context of each multimodal instance. To enhance the model's robustness, we introduce a probabilistic fusion method to fuse output predictions from multiple diverse prompts for each input. Our extensive experiments on six datasets demonstrate the effectiveness of our approach. First, our method outperforms strong baselines in the multimodal few-shot setting. Furthermore, under the same amount of data (1% of the full dataset), our CDS-based experimental results significantly outperform those based on previously sampled datasets constructed from the same number of instances of each class.

The sparseness and incompleteness of knowledge graphs (KGs) trigger considerable interest in enhancing the representation learning with external corpora. However, the difficulty of aligning entities and relations with external corpora leads to inferior performance improvement. Open knowledge graphs (OKGs) consist of entity-mentions and relation-mentions that are represented by noncanonicalized freeform phrases, which generally do not rely on the specification of ontology schema. The roughness of the nonontological construction method leads to a specific characteristic of OKGs: diversity, where multiple entity-mentions (or relation-mentions) have the same meaning but different expressions. The diversity of OKGs can provide potential textual and structural features for the representation learning of KGs. We speculate that leveraging OKGs to enhance the representation learning of KGs can be more effective than using pure text or pure structure corpora. In this paper, we propose a newOERL,Open knowledge graphEnhancedRepresentationLearning of KGs. OERL automatically extracts textual and structural connections between KGs and OKGs, models and transfers refined profitable features to enhance the representation learning of KGs. The strong performance improvement and exhaustive experimental analysis prove the superiority of OERL over state-of-the-art baselines.

In an open-domain dialogue system, the consistent persona is a key factor to generate real and coherent dialogues. Existing methods suffer from the incomprehensive persona tags that have unique and obscure meanings to describe human’s personality. Besides, the addressee information, which is closely related to express personality in multi-party dialogues, has been neglected. In this paper, we construct a multi-party personalized dialogue dataset and propose a graph convolution network model (PersonaTKG) with addressee selecting mechanism that integrates personas, dialogue utterances, and external text knowledge in a unified graph. Extensive experiments have shown that PersonaTKG outperforms the baselines by large margins and effectively improves persona consistency in the generated responses.

Building dialogue generation systems in a zero-shot scenario remains a huge challenge, since the typical zero-shot approaches in dialogue generation rely heavily on large-scale pre-trained language generation models such as GPT-3 and T5. The research on zero-shot dialogue generation without cumbersome language models is limited due to lacking corresponding parallel dialogue corpora. In this paper, we propose a simple but effective Multilingual learning framework for Zero-shot Dialogue Generation (dubbed as MulZDG) that can effectively transfer knowledge from an English corpus with large-scale training samples to a non-English corpus with zero samples. Besides, MulZDG can be viewed as a multilingual data augmentation method to improve the performance of the resource-rich language. First, we construct multilingual code-switching dialogue datasets via translation utterances randomly selected from monolingual English datasets. Then we employ MulZDG to train a unified multilingual dialogue model based on the code-switching datasets. The MulZDG can conduct implicit semantic alignment between different languages. Experiments on DailyDialog and DSTC7 datasets demonstrate that MulZDG not only achieve competitive performance under zero-shot case compared to training with sufficient examples but also greatly improve the performance of the source language.

Sentiment analysis has always been an important research direction in natural language processing. The research can be divided into explicit sentiment analysis and implicit sentiment analysis according to whether there are sentiment words in language expression. There have been many research results in explicit sentiment analysis. However, implicit sentiment analysis is rarely studied. Compared with explicit sentiment expression, implicit sentiment expression usually omits a lot of knowledge and common sense, and context also has an important impact on implicit sentiment expression. In this paper, we use a knowledge graph to supplement implicit sentiment expression and propose a novel Implicit Sentiment Analysis model combining Knowledge enhancement and Context features (dubbed KC-ISA). The KC-ISA model can effectively integrate external knowledge and contextual features by the coattention mechanism. Finally, we conduct experiments on the SMP2019 implicit sentiment analysis dataset. Moreover, to verify the generality of the model, we also conduct experiments on two common sentiment analysis datasets. The results on three datasets show that our proposed KC-ISA model can achieve better results on text sentiment analysis.

Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms.Although promising results have been achieved, these models often suffer from slow inference or huge number of parameters.In this paper, we propose a novel lightweight fully convolutional architecture, called DialogConv, for response selection.DialogConv is exclusively built on top of convolution to extract matching features of context and response.Dialogues are modeled in 3D views, where DialogConv performs convolution operations on embedding view, word view and utterance view to capture richer semantic information from multiple contextual views.On the four benchmark datasets, compared with state-of-the-art baselines, Di-alogConv is on average about 8.5× smaller in size, and 79.39× and 10.64× faster on CPU and GPU devices, respectively.At the same time, DialogConv achieves the competitive effectiveness of response selection.

The incompleteness of knowledge graphs triggers considerable research interest in relation prediction. As the key to predicting relations among entities, many efforts have been devoted to learning the embeddings of entities and relations by incorporating a variety of neighbors' information which includes not only the information from direct outgoing and incoming neighbors but also the ones from the indirect neighbors on the multihop paths. However, previous models usually consider entity paths of limited length or ignore sequential information of the paths. Either simplification will make the model lack a global understanding of knowledge graphs and may result in the loss of important and indispensable information. In this article, we propose a novel global graph attention embedding network (GGAE) for relation prediction by combining global information from both direct neighbors and multihop neighbors. Concretely, given a knowledge graph, we first introduce the path construction algorithms to obtain meaningful paths, then design path modeling methods to capture the potential long-distance sequential information in the multihop paths, final propose an entity graph attention and a relation graph attention mechanisms to obtain entity embeddings and relation embeddings. Moreover, an entity graph attention mechanism is proposed to calculate the entity embeddings by aggregating direct incoming and outgoing neighbors from: 1) an original knowledge graph with the original entity and relation embeddings and 2) a new knowledge graph constructed by the paths whose embeddings are updated by path modeling methods. for each relation, we construct a new graph with related entities and present a relation graph attention to learn the features. Therefore, our model can encapsulate the information from different distance neighbors, and enable the embeddings of entities and relations to better capture all-sided semantic information. The experimental results on benchmark datasets verify the superiority of our model over the state-of-the-art ones.

We investigate response selection for multi-turn conversation in retrieval-based chatbots. Existing studies pay more attention to the matching between utterances and responses by calculating the matching score based on learned features, leading to insufficient model reasoning ability. In this paper, we propose a graph- reasoning network (GRN) to address the problem. GRN first conducts pre-training based on ALBERT using next utterance prediction and utterance order prediction tasks specifically devised for response selection. These two customized pre-training tasks can endow our model with the ability of capturing semantical and chronological dependency between utterances. We then fine-tune the model on an integrated network with sequence reasoning and graph reasoning structures. The sequence reasoning module conducts inference based on the highly summarized context vector of utterance-response pairs from the global perspective. The graph reasoning module conducts the reasoning on the utterance-level graph neural network from the local perspective. Experiments on two conversational reasoning datasets show that our model can dramatically outperform the strong baseline methods and can achieve performance which is close to human-level.

Xiaocui Yang, Shi Feng, Yifei Zhang, Daling Wang. 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.

We study the task of span-level emotion cause analysis (SECA), which is focused on identifying the specific emotion cause span(s) triggering a certain emotion in the text. Compared to the popular clause-level emotion cause analysis (CECA), it is a finer-grained emotion cause analysis (ECA) task. In this paper, we design a BERT-based graph attention network for emotion cause span(s) identification. The proposed model takes advantage of the structure of BERT to capture the relationship information between emotion and text, and utilizes graph attention network to model the structure information of the text. Our SECA method can be easily used for extracting clause-level emotion causes for CECA as well. Experimental results show that the proposed method consistently outperforms the state-of-the-art ECA methods on benchmark emotion cause dataset.

This paper addresses the task of span-level emotion cause analysis (SECA). It is a finer-grained emotion cause analysis (ECA) task, which aims to identify the specific emotion cause span(s) behind certain emotions in text. In this paper, we formalize SECA as a sequence tagging task for which several variants of neural network-based sequence tagging models to extract specific emotion cause span(s) in the given context. These models combine different types of encoding and decoding approaches. Furthermore, to make our models more "emotionally sensitive'', we utilize the multi-head attention mechanism to enhance the representation of context. Experimental evaluations conducted on two benchmark datasets demonstrate the effectiveness of the proposed models.

In open-domain dialogue systems, knowledge information such as unstructured persona profiles, text descriptions and structured knowledge graph can help incorporate abundant background facts for delivering more engaging and informative responses. Existing studies attempted to model a general posterior distribution over candidate knowledge by considering the entire response utterance as a whole at the beginning of decoding process for knowledge selection. However, a single smooth distribution could fail to model the variability of knowledge selection patterns over different decoding steps, and make the knowledge expression less consistent. To remedy this issue, we propose an adaptive posterior knowledge selection framework, which sequentially introduces a series of discriminative distributions to dynamically control when and what knowledge should be used in specific decoding steps. The adaptive distributions can also capture knowledge-relevant semantic dependencies between adjacent words to refine response generation. In particular, for knowledge graph-grounded dialogue generation, we further incorporate the adaptive distributions into generative word distributions to help express the knowledge entity words. The experimental results show that our developed methods outperform strong baseline systems by large margins.

Compared with single-modal content, multimodal data can express users’ feelings and sentiments more vividly and interestingly. Therefore, multimodal sentiment analysis has become a popular research topic. However, most existing methods either learn modal sentiment feature independently, without considering their correlations, or they simply integrate multimodal features. In addition, most publicly available multimodal datasets are labeled by sentiment polarities, while the emotions expressed by users are specific. Based on this observation, in this paper, we build a large-scale image-text emotion dataset (i.e., labeled by different emotions), called TumEmo, with more than190,000instances from Tumblr.1We further propose a novel multimodal emotion analysis model based on the Multi-view Attentional Network (MVAN), which utilizes a memory network that is continually updated to obtain the deep semantic features of image-text. The model includes three stages: feature mapping, interactive learning, and feature fusion. In the feature mapping stage, we leverage image features from an object viewpoint and a scene viewpoint to capture effective information for multimodal emotion analysis. Then, an interactive learning mechanism is adopted that uses the memory network; this mechanism extracts single-modal emotion features and interactively models the cross-view dependencies between the image and text. In the feature fusion stage, multiple features are deeply fused using a multilayer perceptron and a stacking-pooling module. The experimental results on the MVSA-Single, MVSA-Multiple, and TumEmo datasets show that the proposed MVAN outperforms strong baseline models by large margins.

Generating emotional responses is crucial for building human-like dialogue systems. However, existing studies have focused only on generating responses by controlling the agents' emotions, while the feelings of the users, which are the ultimate concern of a dialogue system, have been neglected. In this paper, we propose a novel variational model named EmoElicitor to generate appropriate responses that can elicit user's specific emotion. We incorporate the next-round utterance after the response into the posterior network to enrich the context, and we decompose single latent variable into several sequential ones to guide response generation with the help of a pre-trained language model. Extensive experiments conducted on real-world dataset show that EmoElicitor not only performs better than the baselines in term of diversity and semantic similarity, but also can elicit emotion with higher accuracy.

In open-domain dialogue systems, dialogue cues such as emotion, persona, and emoji can be incorporated into conversation models for strengthening the semantic relevance of generated responses. Existing neural response generation models either incorporate dialogue cue into decoder’s initial state or embed the cue indiscriminately into the state of every generated word, which may cause the gradients of the embedded cue to vanish or disturb the semantic relevance of generated words during back propagation. In this paper, we propose a Cue Adaptive Decoder (CueAD) that aims to dynamically determine the involvement of a cue at each generation step in the decoding. For this purpose, we extend the Gated Recurrent Unit (GRU) network with an adaptive cue representation for facilitating cue incorporation, in which an adaptive gating unit is utilized to decide when to incorporate cue information so that the cue can provide useful clues for enhancing the semantic relevance of the generated words. Experimental results show that CueAD outperforms state-of-the-art baselines with large margins.

Weichao Wang, Shi Feng, Daling Wang, Yifei Zhang. 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.

Emotion cause analysis has been a key topic in natural language processing. Existing methods ignore the contexts around the emotion word which can provide an emotion cause clue. Meanwhile, the clauses in a document play different roles on stimulating a certain emotion, depending on their content relevance. Therefore, we propose a co-attention neural network model for emotion cause analysis with emotional context awareness. The method encodes the clauses with a co-attention based bi-directional long short-term memory into high-level input representations, which are further fed into a convolutional layer for emotion cause analysis. Experimental results show that our approach outperforms the state-of-the-art baseline methods.

Sentiment expression in microblog posts can be affected by user's personal character, opinion bias, political stance and so on. Most of existing personalized microblog sentiment classification methods suffer from the insufficiency of discriminative tweets for personalization learning. We observed that microblog users have consistent individuality and opinion bias in different languages. Based on this observation, in this paper we propose a novel user-attention-based Convolutional Neural Network (CNN) model with adversarial cross-lingual learning framework. The user attention mechanism is leveraged in CNN model to capture user's language-specific individuality from the posts. Then the attention-based CNN model is incorporated into a novel adversarial cross-lingual learning framework, in which with the help of user properties as bridge between languages, we can extract the language-specific features and language-independent features to enrich the user post representation so as to alleviate the data insufficiency problem. Results on English and Chinese microblog datasets confirm that our method outperforms state-of-the-art baseline algorithms with large margins.

Review rating prediction is an important research topic. The problem was approached from either the perspective of recommender systems (RS) or that of sentiment analysis (SA). Recent SA research using deep neural networks (DNNs) has realized the importance of user and product interaction for better interpreting the sentiment of reviews. However, the complexity of DNN models in terms of the scale of parameters is very high, and the performance is not always satisfying especially when user-product interaction is sparse. In this paper, we propose a simple, extensible RS-based model, called Text-driven Latent Factor Model (TLFM), to capture the semantics of reviews, user preferences and product characteristics by jointly optimizing two components, a user-specific LFM and a product-specific LFM, each of which decomposes text into a specific low-dimension representation. Furthermore, we address the cold-start issue by developing a novel Pairwise Rating Comparison strategy (PRC), which utilizes the difference between ratings on common user/product as supplementary information to calibrate parameter estimation. Experiments conducted on IMDB and Yelp datasets validate the advantage of our approach over state-of-the-art baseline methods.

In the research of building emotion lexicons, we witness the exploitation of crowd-sourced affective annotation given by readers of online news articles. Such approach ignores the relationship between topics and emotion expressions which are often closely correlated. We build an emotion lexicon by developing a novel joint non-negative matrix factorization model which not only incorporates crowd-annotated emotion labels of articles but also generates the lexicon using the topic-specific matrices obtained from the factorization process. We evaluate our lexicon via emotion classification on both benchmark and built-in-house datasets. Results demonstrate the high-quality of our lexicon.

Most existing sentiment analysis methods focus on single-label classification, which means only a exclusive sentiment orientation (negative, positive or neutral) or an emotion state (joy, hate, love, sorrow, anxiety, surprise, anger, or expect) is considered for the given text. However, multiple emotions with different intensity may be coexisting in one document, one paragraph or even in one sentence. In this paper, we propose a fuzzy-rough set based approach to detect the multi-labeled emotions and calculate their corresponding intensities in social media text. Using the proposed fuzzy-rough set method, we can simultaneously model multi emotions and their intensities with sentiment words for a sentence, a paragraph, or a document. Experiments on a well-known blog emotion corpus show that our proposed multi-labeled emotion intensity analysis algorithm outperforms baseline methods by a large margin.

Roles, their emotion, and interactions between them are three key elements for semantic content understanding of movies. In this paper, we proposed a novel movie summarization method to capture the semantic content in movies based on a string of IE-RoleNets. An IE-RoleNet (interaction and emotion rolenet) models the emotion and interactions of roles in a shot of the movie. The whole movie is represented as a string of IE-RoleNets. Summarization of a movie is transformed into finding an optimal substring with user-specified summarization ratio. Hierarchical substring mining is conducted to find an optimal substring of the whole movie. We have conducted objective and subjective experiments on our method. Experimental results show the ability of our method to capture the semantic content of movies.

Extensive experiments have validated the effectiveness of the corpus-based method for classifying the word's sentiment polarity.However, no work is done for comparing different corpora in the polarity classification task.Nowadays, Twitter has aggregated huge amount of data that are full of people's sentiments.In this paper, we empirically evaluate the performance of different corpora in sentiment similarity measurement, which is the fundamental task for word polarity classification.Experiment results show that the Twitter data can achieve a much better performance than the Google, Web1T and Wikipedia based methods.

Traditional Web crawlers use one or more URLs of the initial Webpages to extract new URLs continuously, and then access data of the pages. AJAX, as one of the core technologies of Web2.0, greatly enhances the response efficiency of Web applications, brings good user experience, and therefore has been widely used. However, due to the use of AJAX techniques shatters the architecture of traditional Web pages which is based on static pages, the traditional Web crawlers cannot meet the challenges of dynamic partial refresh and asynchronous loading. In this paper, we propose an efficient approach for the information in dynamic pages by analyzing script language, and use path repository and judge the page refreshing state to improve the accuracy and efficiency of the algorithm. Experimental evaluation shows the efficiency and effectiveness of our approach.