Keyang Ding
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Keyang Ding has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Qianlong Wang
Harbin Institute of Technology, Shenzhen, China
10 shared publications - Ruifeng Xu
Harbin Institute of Technology, Shenzhen, China
10 shared publications - Bin Liang
The Chinese University of Hong Kong, Hong Kong, China
4 shared publications - Zhiyuan Wen
School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China
3 shared publications - Hengxin Gao
Institute of High Energy Physics Key Laboratory for Particle Astrophysics Chinese Academy of Sciences 19B Yuquan Road 100049 Beijing China
2 shared publications - Bingbing Wang
Harbin Institute of Technology, Shenzhen, China
1 shared publication
Latest Publications
- 22 August 2026
- Published by Elsevier in Neurocomputing
- Vol. 705
Beyond aggregated labels: Personalized reader emotion prediction via LLM-based persona reasoning
- 22 August 2026
- Published by Elsevier in Neurocomputing
- Vol. 705
Beyond aggregated labels: Personalized reader emotion prediction via LLM-based persona reasoning
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 2539-2551
Enhancing Multimodal Reasoning via Visual Semantic Summarization
Recent advances in multimodal large models (MLMs) have enabled promising progress in multimodal reasoning. However, due to multimodal misalignment and language-dominant representations, MLMs often compress or lose fine-grained visual semantics. As a result, they struggle to (1) reliably perceive task-relevant visual details and (2) effectively leverage parametric knowledge conditioned on visual evidence. These limitations ultimately lead to unreliable reasoning outcomes. To address these limitations, we introduce a simple yet effective framework built upon visual semantic summarization. Our framework iteratively optimizes two complementary stages: one for generating high-quality visual semantic summaries containing reasoning-critical visual semantics, and another for strengthening the MLM's ability to utilize such summaries during multimodal inference. Acting as compact visual auxiliaries, the summaries guide attention toward fine-grained clues and facilitate knowledge retrieval from internal parameters. Extensive experiments on six multimodal reasoning benchmarks spanning three tasks (VQA, MABSA, and HMD) show that our framework consistently outperforms existing MLMs-based methods.
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 2539-2551
Enhancing Multimodal Reasoning via Visual Semantic Summarization
Recent advances in multimodal large models (MLMs) have enabled promising progress in multimodal reasoning. However, due to multimodal misalignment and language-dominant representations, MLMs often compress or lose fine-grained visual semantics. As a result, they struggle to (1) reliably perceive task-relevant visual details and (2) effectively leverage parametric knowledge conditioned on visual evidence. These limitations ultimately lead to unreliable reasoning outcomes. To address these limitations, we introduce a simple yet effective framework built upon visual semantic summarization. Our framework iteratively optimizes two complementary stages: one for generating high-quality visual semantic summaries containing reasoning-critical visual semantics, and another for strengthening the MLM's ability to utilize such summaries during multimodal inference. Acting as compact visual auxiliaries, the summaries guide attention toward fine-grained clues and facilitate knowledge retrieval from internal parameters. Extensive experiments on six multimodal reasoning benchmarks spanning three tasks (VQA, MABSA, and HMD) show that our framework consistently outperforms existing MLMs-based methods.
- 17 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 282
CRC-MRC: Reader Comments Augmented Machine Reading Comprehension for social emotion prediction
- 17 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 282
CRC-MRC: Reader Comments Augmented Machine Reading Comprehension for social emotion prediction
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18630-18646
Error Comparison Optimization for Large Language Models on Aspect-Based Sentiment Analysis
Qianlong Wang, Keyang Ding, Hengxin Gao, Hui Wang, Ruifeng Xu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18630-18646
Open AccessError Comparison Optimization for Large Language Models on Aspect-Based Sentiment Analysis
Qianlong Wang, Keyang Ding, Hengxin Gao, Hui Wang, Ruifeng Xu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 22 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (1) , 264-276
Cross-Domain Sentiment Analysis via Disentangled Representation and Prototypical Learning
Cross-domain sentiment analysis (CDSA) aims to predict the sentiment polarities of reviews in the target domain using a sentiment classifier learned from the source labeled domain. Most existing studies are dominant with adversarial learning methods and focus on learning domain-invariant sentiment representations in both the source and target domains. However, since sentiment-specific features are not explicitly decoupled, the model may confuse domain features with sentiment features, thus affecting its generalization ability on target domains. Unlike previous studies, in this paper, we tackle the CDSA task from the view of disentangled representation learning, which explicitly learns the disentangled representations of review, focusing in particular on sentiment and domain semantics. Specifically, we disentangle sentiment-specific and domain-specific features from the text representation of the review by two different linear transformations. Then, we introduce a straightforward disentangled loss to disallow the sentiment-specific feature to capture domain information. Moreover, we leverage target unlabeled data to improve the quality of the learned sentiment-specific features via prototypical learning. It indirectly encourages the sentiment-specific features of target samples having potentially different classes more discriminative. Extensive experiments on widely used CDSA datasets show that our method surpasses competitive baselines and achieves new state-of-the-art results, demonstrating its effectiveness and superiority.
- 22 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (1) , 264-276
Cross-Domain Sentiment Analysis via Disentangled Representation and Prototypical Learning
Cross-domain sentiment analysis (CDSA) aims to predict the sentiment polarities of reviews in the target domain using a sentiment classifier learned from the source labeled domain. Most existing studies are dominant with adversarial learning methods and focus on learning domain-invariant sentiment representations in both the source and target domains. However, since sentiment-specific features are not explicitly decoupled, the model may confuse domain features with sentiment features, thus affecting its generalization ability on target domains. Unlike previous studies, in this paper, we tackle the CDSA task from the view of disentangled representation learning, which explicitly learns the disentangled representations of review, focusing in particular on sentiment and domain semantics. Specifically, we disentangle sentiment-specific and domain-specific features from the text representation of the review by two different linear transformations. Then, we introduce a straightforward disentangled loss to disallow the sentiment-specific feature to capture domain information. Moreover, we leverage target unlabeled data to improve the quality of the learned sentiment-specific features via prototypical learning. It indirectly encourages the sentiment-specific features of target samples having potentially different classes more discriminative. Extensive experiments on widely used CDSA datasets show that our method surpasses competitive baselines and achieves new state-of-the-art results, demonstrating its effectiveness and superiority.
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2462-2466
Improving In-Context Learning via Sequentially Selection and Preference Alignment for Few-Shot Aspect-Based Sentiment Analysis
In this paper, we leverage in-context learning (ICL) paradigm to handle few-shot aspect-based sentiment analysis (ABSA). Previous works first rank candidate examples by some metrics and then independently retrieve examples similar to test samples. However, their effectiveness may be discounted because of two limitations: in-context example redundancy and example preference misalignment between retriever and LLM. To alleviate them, we propose a novel framework that sequentially retrieves in-context examples. It not only considers which example is useful for the test sample but also prevents its information from being duplicated by already retrieved examples. Subsequently, we exploit the rewards of LLMs on retrieved in-context examples to optimize parameters for bridging preference gaps. Experiments on four ABSA datasets show that our framework is significantly superior to previous works.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2462-2466
Open AccessImproving In-Context Learning via Sequentially Selection and Preference Alignment for Few-Shot Aspect-Based Sentiment Analysis
In this paper, we leverage in-context learning (ICL) paradigm to handle few-shot aspect-based sentiment analysis (ABSA). Previous works first rank candidate examples by some metrics and then independently retrieve examples similar to test samples. However, their effectiveness may be discounted because of two limitations: in-context example redundancy and example preference misalignment between retriever and LLM. To alleviate them, we propose a novel framework that sequentially retrieves in-context examples. It not only considers which example is useful for the test sample but also prevents its information from being duplicated by already retrieved examples. Subsequently, we exploit the rewards of LLMs on retrieved in-context examples to optimize parameters for bridging preference gaps. Experiments on four ABSA datasets show that our framework is significantly superior to previous works.
- 2 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11 (3) , 3362-3375
LCSEP: A Large-Scale Chinese Dataset for Social Emotion Prediction to Online Trending Topics
In this article, we present our work in social emotion prediction to online trending topics. While most prior works focus on emotion from writers or the readers’ emotions evoked by news articles, we investigate discussions from massive social media users and explore the public feelings to the online trending topic. We employ user-generated “#hashtags” to indicate online trending topics and construct a large-scale Chinese dataset for social emotion prediction (LCSEP) to trending topics collected from the Chinese microblog Sina Weibo. It contains more than 20 000 trending topics, each with social emotions voted in 24 fine-grained types, and gathers hashtags, posts, comments, and related metadata to give each trending topic a thorough context. We also propose a Hashtag- and Topic-Enhanced Attention Model (HTEAM) that combines a pretrained BERT model, a neural topic model, and an attention mechanism via joint training to understand social emotion. Experiments show that HTEAM outperforms baselines and achieves the state-of-the-art result.
- 2 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11 (3) , 3362-3375
LCSEP: A Large-Scale Chinese Dataset for Social Emotion Prediction to Online Trending Topics
In this article, we present our work in social emotion prediction to online trending topics. While most prior works focus on emotion from writers or the readers’ emotions evoked by news articles, we investigate discussions from massive social media users and explore the public feelings to the online trending topic. We employ user-generated “#hashtags” to indicate online trending topics and construct a large-scale Chinese dataset for social emotion prediction (LCSEP) to trending topics collected from the Chinese microblog Sina Weibo. It contains more than 20 000 trending topics, each with social emotions voted in 24 fine-grained types, and gathers hashtags, posts, comments, and related metadata to give each trending topic a thorough context. We also propose a Hashtag- and Topic-Enhanced Attention Model (HTEAM) that combines a pretrained BERT model, a neural topic model, and an attention mechanism via joint training to understand social emotion. Experiments show that HTEAM outperforms baselines and achieves the state-of-the-art result.
- Open Access
- 14 June 2023
- Published by MDPI AG in Electronics
- Vol. 12 (12) , 2673
RDVI: A Retrieval–Detection Framework for Verbal Irony Detection
Verbal irony is a common form of expression used in daily communication, where the intended meaning is often opposite to the literal meaning. Accurately recognizing verbal irony is essential for any NLP application for which the understanding of the true user intentions is key to performing the underlying tasks. While existing research has made progress in this area, verbal irony often involves connotative knowledge that cannot be directly inferred from the text or its context, which limits the detection model’s ability to recognize and comprehend verbal irony. To address this issue, we propose a Retrieval–Detection method for Verbal Irony (RDVI). This approach improves the detection model’s ability to recognize and comprehend verbal irony by retrieving the connotative knowledge from the open domain and incorporating it into the model using prompt learning. The experimental results demonstrate that our proposed method outperforms state-of-the-art models.
- 14 June 2023
- Published by MDPI AG in Electronics
- Vol. 12 (12) , 2673
Open AccessRDVI: A Retrieval–Detection Framework for Verbal Irony Detection
Verbal irony is a common form of expression used in daily communication, where the intended meaning is often opposite to the literal meaning. Accurately recognizing verbal irony is essential for any NLP application for which the understanding of the true user intentions is key to performing the underlying tasks. While existing research has made progress in this area, verbal irony often involves connotative knowledge that cannot be directly inferred from the text or its context, which limits the detection model’s ability to recognize and comprehend verbal irony. To address this issue, we propose a Retrieval–Detection method for Verbal Irony (RDVI). This approach improves the detection model’s ability to recognize and comprehend verbal irony by retrieving the connotative knowledge from the open domain and incorporating it into the model using prompt learning. The experimental results demonstrate that our proposed method outperforms state-of-the-art models.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 2930-2941
Reducing Spurious Correlations in Aspect-based Sentiment Analysis with Explanation from Large Language Models
Qianlong Wang, Keyang Ding, Bin Liang, Min Yang, Ruifeng Xu. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 2930-2941
Open AccessReducing Spurious Correlations in Aspect-based Sentiment Analysis with Explanation from Large Language Models
Qianlong Wang, Keyang Ding, Bin Liang, Min Yang, Ruifeng Xu. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.
- 16 December 2022
- Published by Springer Nature
- p. 49-63
Frequently Asked Question Pair Generation for Rule and Regulation Document
- 16 December 2022
- Published by Springer Nature
- p. 49-63
Frequently Asked Question Pair Generation for Rule and Regulation Document