Hongkui Tu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hongkui Tu has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Aixin Sun
Nanyang technological university, Singapore, Singapore
3 shared publications Xiaodong Wang
National Laboratory of Parallel and Distributed Processing, National University of Defense Technology, Changsha, Hunan, China
3 shared publicationsAiping Li
National University of Defense Technology, 109 Deya Road, Changsha, 410003, Hunan, China
2 shared publications- Han Yu
Nanyang technological university, Singapore, Singapore
2 shared publications - Kai Chen
National university of defense technology, Changsha, China
2 shared publications - Ziniu Liu
National university of defense technology, Changsha, China
2 shared publications
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 728-737
Robust Multi-modal Knowledge Graph Completion via Modality-Specific Experts
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 728-737
Open AccessRobust Multi-modal Knowledge Graph Completion via Modality-Specific Experts
- 28 August 2024
- Published by Elsevier in Neurocomputing
- Vol. 609
Inductive relation prediction with information bottleneck
- 28 August 2024
- Published by Elsevier in Neurocomputing
- Vol. 609
Inductive relation prediction with information bottleneck
- 12 April 2024
- Published by Springer Nature in World Wide Web
- Vol. 27 (3) , 1-19
Generalizable inductive relation prediction with causal subgraph
- 12 April 2024
- Published by Springer Nature in World Wide Web
- Vol. 27 (3) , 1-19
Generalizable inductive relation prediction with causal subgraph
- 24 September 2022
- Published by Springer Nature
- p. 311-323
ArgumentPrompt: Activating Multi-category of Information for Event Argument Extraction with Automatically Generated Prompts
- 24 September 2022
- Published by Springer Nature
- p. 311-323
ArgumentPrompt: Activating Multi-category of Information for Event Argument Extraction with Automatically Generated Prompts
- Open Access
Hierarchical Text Interaction for Rating Prediction
Traditional recommender systems encounter several challenges such as data sparsity and unexplained recommendation. To address these challenges, many works propose to exploit semantic information from review data. However, these methods have two major limitations in terms of the way to model textual features and capture textual interaction. For textual modeling, they simply concatenate all the reviews of a user/item into a single review. However, feature extraction at word/phrase level can violate the meaning of the original reviews. As for textual interaction, they defer the interactions to the prediction layer, making them fail to capture complex correlations between users and items. To address those limitations, we propose a novel Hierarchical Text Interaction model(HTI) for rating prediction. In HTI, we propose to model low-level word semantics and high-level review representations hierarchically. The hierarchy allows us to exploit textual features at different granularities. To further capture complex user-item interactions, we propose to exploit semantic correlations between each user-item pair at different hierarchies. At word level, we propose an attention mechanism specialized to each user-item pair, and capture the important words for representing each review. At review level, we mutually propagate textual features between the user and item, and capture the informative reviews. The aggregated review representations are integrated into a collaborative filtering framework for rating prediction. Experiments on five real-world datasets demonstrate that HTI outperforms state-of-the-art models by a large margin. Further case studies provide a deep insight into HTI's ability to capture semantic correlations at different levels of granularities for rating prediction.
Open AccessHierarchical Text Interaction for Rating Prediction
Traditional recommender systems encounter several challenges such as data sparsity and unexplained recommendation. To address these challenges, many works propose to exploit semantic information from review data. However, these methods have two major limitations in terms of the way to model textual features and capture textual interaction. For textual modeling, they simply concatenate all the reviews of a user/item into a single review. However, feature extraction at word/phrase level can violate the meaning of the original reviews. As for textual interaction, they defer the interactions to the prediction layer, making them fail to capture complex correlations between users and items. To address those limitations, we propose a novel Hierarchical Text Interaction model(HTI) for rating prediction. In HTI, we propose to model low-level word semantics and high-level review representations hierarchically. The hierarchy allows us to exploit textual features at different granularities. To further capture complex user-item interactions, we propose to exploit semantic correlations between each user-item pair at different hierarchies. At word level, we propose an attention mechanism specialized to each user-item pair, and capture the important words for representing each review. At review level, we mutually propagate textual features between the user and item, and capture the informative reviews. The aggregated review representations are integrated into a collaborative filtering framework for rating prediction. Experiments on five real-world datasets demonstrate that HTI outperforms state-of-the-art models by a large margin. Further case studies provide a deep insight into HTI's ability to capture semantic correlations at different levels of granularities for rating prediction.
- Open Access
- 13 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 73081-73092
Joint Implicit and Explicit Neural Networks for Question Recommendation in CQA Services
Community Question Answering (CQA) services have emerged as a type of popular social platforms. In the social network, experts provide knowledgeable answers to the questions in their domain of expertise, while celebrities publish influential opinions towards the topics led by some questions. Given the large amount of knowledge organized in the format of question-answers, an interesting research problem is to recommend questions to users so as to maximize their engagements with the platform. However, recommending questions in CQA services is a non-trivial task. Data sources in the CQA services are of different types. It is challenging to incorporate heterogeneous information for the recommendation task. Further, data sparsity is an inherent problem in such platforms. In this paper, we propose a model that is able to jointly model both implicit and explicit information for question recommendation. The model integrates multiple data sources and addresses the problem of data heterogeneity. In the proposed model, we dynamically discover latent user groups and incorporate those hierarchical information to bridge the semantic gaps among users in the shared latent space. We evaluate the proposed model on two real-world datasets, and demonstrate that our model outperforms state-of-the-art alternatives by a large margin. We also investigate different structures of the proposed model to study the effects of different data sources.
- 13 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 73081-73092
Open AccessJoint Implicit and Explicit Neural Networks for Question Recommendation in CQA Services
Community Question Answering (CQA) services have emerged as a type of popular social platforms. In the social network, experts provide knowledgeable answers to the questions in their domain of expertise, while celebrities publish influential opinions towards the topics led by some questions. Given the large amount of knowledge organized in the format of question-answers, an interesting research problem is to recommend questions to users so as to maximize their engagements with the platform. However, recommending questions in CQA services is a non-trivial task. Data sources in the CQA services are of different types. It is challenging to incorporate heterogeneous information for the recommendation task. Further, data sparsity is an inherent problem in such platforms. In this paper, we propose a model that is able to jointly model both implicit and explicit information for question recommendation. The model integrates multiple data sources and addresses the problem of data heterogeneity. In the proposed model, we dynamically discover latent user groups and incorporate those hierarchical information to bridge the semantic gaps among users in the shared latent space. We evaluate the proposed model on two real-world datasets, and demonstrate that our model outperforms state-of-the-art alternatives by a large margin. We also investigate different structures of the proposed model to study the effects of different data sources.
- 14 October 2017
- Published by Springer Nature
- p. 681-694
Entity Recognition by Distant Supervision with Soft List Constraint
- 14 October 2017
- Published by Springer Nature
- p. 681-694
Entity Recognition by Distant Supervision with Soft List Constraint
- 15 October 2016
- Published by Springer Nature
- p. 356-362
When MetaMap Meets Social Media in Healthcare: Are the Word Labels Correct?
- 15 October 2016
- Published by Springer Nature
- p. 356-362
When MetaMap Meets Social Media in Healthcare: Are the Word Labels Correct?