Dexi Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Dexi Liu has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Changxuan Wan
School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, China
8 shared publications - Xiping Liu
Jiangxi University of Finance and Economics
8 shared publications - Qizhi Wan
School of Information Technology, Jiangxi University of Finance and Economics
7 shared publications - Keli Xiao
Stony Brook University
4 shared publications - Rong Hu
Jiangxi University of Finance and Economics
3 shared publications - Guoqiong Liao
Modern Industry School of Virtual Reality, Jiangxi University of Finance and Economics
2 shared publications
Latest Publications
- Open Access
- 23 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 25 (8) , 1-22
Suicide Risk Assessment via Emotion-Time Perception for Social Network Users
Using text data from social network users for suicide risk assessment offers convenience, timeliness, and non-intrusiveness. User emotions are a crucial factor in determining suicide risk and have been extensively studied in research. However, current methods primarily focus on the accumulation of users’ historical emotions, neglecting the changes in emotions and not delving into the time points within historical key emotions. To address this issue, we propose the Emotion-Time-Aware (ETA) model, designed to improve the accuracy of suicide risk assessments. The model consists of three main modules: the Emotional Changes Perception (ECP), the Key Emotion Time Point Perception (KETPP), and the Emotion Perception Fusion (EPF) modules. The ECP module integrates the time, emotion and semantic information of the posts, facilitating the interaction of historical emotions at different time points and capturing the changes in the emotions of users. The KETPP module uses an attention mechanism to identify key emotion time points from users’ historical posts, which are crucial for evaluating suicidal ideation. Finally, the EPF module integrates the emotional changes and key emotion time points to form a comprehensive representation of the users’ posts, thereby assessing their suicide risk level. We evaluate the ETA along with other baseline models on the CLPsych2017 and CLPsych2019 datasets. The results show that the ETA model achieved the highest accuracy and All- F 1 score on both datasets, validating its effectiveness in suicide risk assessment.
- 23 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 25 (8) , 1-22
Open AccessSuicide Risk Assessment via Emotion-Time Perception for Social Network Users
Using text data from social network users for suicide risk assessment offers convenience, timeliness, and non-intrusiveness. User emotions are a crucial factor in determining suicide risk and have been extensively studied in research. However, current methods primarily focus on the accumulation of users’ historical emotions, neglecting the changes in emotions and not delving into the time points within historical key emotions. To address this issue, we propose the Emotion-Time-Aware (ETA) model, designed to improve the accuracy of suicide risk assessments. The model consists of three main modules: the Emotional Changes Perception (ECP), the Key Emotion Time Point Perception (KETPP), and the Emotion Perception Fusion (EPF) modules. The ECP module integrates the time, emotion and semantic information of the posts, facilitating the interaction of historical emotions at different time points and capturing the changes in the emotions of users. The KETPP module uses an attention mechanism to identify key emotion time points from users’ historical posts, which are crucial for evaluating suicidal ideation. Finally, the EPF module integrates the emotional changes and key emotion time points to form a comprehensive representation of the users’ posts, thereby assessing their suicide risk level. We evaluate the ETA along with other baseline models on the CLPsych2017 and CLPsych2019 datasets. The results show that the ETA model achieved the highest accuracy and All- F 1 score on both datasets, validating its effectiveness in suicide risk assessment.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 1659-1673
Role-Pair Event Tracing Graph for Joint Document-Level Event Extraction
Existing studies mostly decompose the document-level event extraction task into several sub-tasks, namely entity extraction, event type detection, and multi-event extraction under recognized event types. These sub-tasks are then executed independently in a step-by-step manner. This induces certain error propagation. Meanwhile, the associated semantics of entities functioning as arguments in multiple events have not been fully exploited, and the path expansion strategy relies heavily on the predefined role order. To address these issues, this paper proposes a novel strategy for joint document-level event extraction. First, inspired by the path expansion strategy, we devise a Role-Pair Event Tracing Graph (RP-ETG) to achieve the multi-event extraction sub-task. In this graph, tokens serve as nodes, with pairs designated as the forward edge types and tracing identifiers as the backward edge types. The forward edges serve to identify the roles that token nodes play in an event, while the backward edges are used to track which token nodes belong to the same event. Next, to determine the event type, this paper sequentially assigns numbers to the role-pair labels across different event types, ensuring that the labels for each event type fall into a distinct numerical interval. Thus, RP-ETG not only enables the accurate decoding of all events within a document, but also directly clarifies the argument roles that tokens assume in specific events under given event types. It can also capture the associated semantics of tokens when they act as arguments across multiple events. Leveraging this graph structure, we develop a graph-enhanced model for joint document-level event extraction. We evaluate the efficacy of our proposed method through exhaustive experiments on two public datasets. The results manifest its superiority over state-of-the-art baselines, validating the significant advancements enabled by our approach.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 1659-1673
Role-Pair Event Tracing Graph for Joint Document-Level Event Extraction
Existing studies mostly decompose the document-level event extraction task into several sub-tasks, namely entity extraction, event type detection, and multi-event extraction under recognized event types. These sub-tasks are then executed independently in a step-by-step manner. This induces certain error propagation. Meanwhile, the associated semantics of entities functioning as arguments in multiple events have not been fully exploited, and the path expansion strategy relies heavily on the predefined role order. To address these issues, this paper proposes a novel strategy for joint document-level event extraction. First, inspired by the path expansion strategy, we devise a Role-Pair Event Tracing Graph (RP-ETG) to achieve the multi-event extraction sub-task. In this graph, tokens serve as nodes, with pairs designated as the forward edge types and tracing identifiers as the backward edge types. The forward edges serve to identify the roles that token nodes play in an event, while the backward edges are used to track which token nodes belong to the same event. Next, to determine the event type, this paper sequentially assigns numbers to the role-pair labels across different event types, ensuring that the labels for each event type fall into a distinct numerical interval. Thus, RP-ETG not only enables the accurate decoding of all events within a document, but also directly clarifies the argument roles that tokens assume in specific events under given event types. It can also capture the associated semantics of tokens when they act as arguments across multiple events. Leveraging this graph structure, we develop a graph-enhanced model for joint document-level event extraction. We evaluate the efficacy of our proposed method through exhaustive experiments on two public datasets. The results manifest its superiority over state-of-the-art baselines, validating the significant advancements enabled by our approach.
- 22 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 306
Automatic contrastive chain-of-thought prompting: Learning from reasoning errors of large language models
- 22 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 306
Automatic contrastive chain-of-thought prompting: Learning from reasoning errors of large language models
- 27 November 2025
- Published by Elsevier in Pattern Recognition Letters
- Vol. 200, 1-7
End-to-end interactive joint model: Clause-phrase multi-task learning for suicidal ideation cause extraction (SICE) in Chinese Weibo text
- 27 November 2025
- Published by Elsevier in Pattern Recognition Letters
- Vol. 200, 1-7
End-to-end interactive joint model: Clause-phrase multi-task learning for suicidal ideation cause extraction (SICE) in Chinese Weibo text
- Open Access
MADP: Multi-Agent Deductive Planning for Enhanced Cognitive-Behavioral Mental Health Question Answer
The Mental Health Question Answer (MHQA) task requires the seeker and supporter to complete the support process in one-turn dialogue. Given the richness of help-seeker posts, supporters must thoroughly understand the content and provide logical, comprehensive, and well-structured responses. Previous works in MHQA mostly focus on single-agent approaches based on the cognitive element of Cognitive Behavioral Therapy (CBT), but they overlook the interactions among various CBT elements, such as emotion and cognition. This limitation hinders the models' ability to thoroughly understand the distress of help-seekers. To address this, we propose a framework named Multi-Agent Deductive Planning (MADP), which is based on the interactions between the various psychological elements of CBT. This method guides Large Language Models (LLMs) to achieve a deeper understanding of the seeker's context and provide more personalized assistance based on individual circumstances. Furthermore, we construct a new dataset based on the MADP framework and use it to fine-tune LLMs, resulting in a specialized model named MADP-LLM. We conduct extensive experiments, including comparisons with multiple LLMs, human evaluations, and automatic evaluations, to validate the effectiveness of the MADP framework and MADP-LLM.
Open AccessMADP: Multi-Agent Deductive Planning for Enhanced Cognitive-Behavioral Mental Health Question Answer
The Mental Health Question Answer (MHQA) task requires the seeker and supporter to complete the support process in one-turn dialogue. Given the richness of help-seeker posts, supporters must thoroughly understand the content and provide logical, comprehensive, and well-structured responses. Previous works in MHQA mostly focus on single-agent approaches based on the cognitive element of Cognitive Behavioral Therapy (CBT), but they overlook the interactions among various CBT elements, such as emotion and cognition. This limitation hinders the models' ability to thoroughly understand the distress of help-seekers. To address this, we propose a framework named Multi-Agent Deductive Planning (MADP), which is based on the interactions between the various psychological elements of CBT. This method guides Large Language Models (LLMs) to achieve a deeper understanding of the seeker's context and provide more personalized assistance based on individual circumstances. Furthermore, we construct a new dataset based on the MADP framework and use it to fine-tune LLMs, resulting in a specialized model named MADP-LLM. We conduct extensive experiments, including comparisons with multiple LLMs, human evaluations, and automatic evaluations, to validate the effectiveness of the MADP framework and MADP-LLM.
- Open Access
- 30 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (1) , 1-36
A Multifocal Graph-Based Neural Network Scheme for Topic Event Extraction
Event extraction is a long-standing and challenging task in natural language processing, and existing studies mainly focus on extracting events within sentences. However, a significant problem that has not been carefully investigated is whether an “event topic” can be identified to represent the main aspects of extracted events. This article formulates the “topic event” extraction problem, aiming to identify a representative event from extracted ones. Specifically, after defining the topic event, we develop a multifocal graph-based framework to handle the extraction task. To enrich the associations of events and their tokens, we construct four event graphs, including the event subgraph and three event-associated graphs (i.e., event dependency parsing graph, event organization graph, and event share token graph), that reflect the internal and external structures of events, respectively. Subsequently, we design a multi-attention event-graph neural network to capture these event graph structures and improve event subgraph embedding. Finally, the output embeddings in the last layer of each channel are concatenated and fed into a fully connected network for topic event recognition. Extensive experiments validate the effectiveness of our method, and the results confirm its superiority over state-of-the-art baselines. In-depth analyses explore the essential factors (e.g., graph structures, attentions, feature generation method, etc.) determining the extraction performance.
- 30 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (1) , 1-36
Open AccessA Multifocal Graph-Based Neural Network Scheme for Topic Event Extraction
Event extraction is a long-standing and challenging task in natural language processing, and existing studies mainly focus on extracting events within sentences. However, a significant problem that has not been carefully investigated is whether an “event topic” can be identified to represent the main aspects of extracted events. This article formulates the “topic event” extraction problem, aiming to identify a representative event from extracted ones. Specifically, after defining the topic event, we develop a multifocal graph-based framework to handle the extraction task. To enrich the associations of events and their tokens, we construct four event graphs, including the event subgraph and three event-associated graphs (i.e., event dependency parsing graph, event organization graph, and event share token graph), that reflect the internal and external structures of events, respectively. Subsequently, we design a multi-attention event-graph neural network to capture these event graph structures and improve event subgraph embedding. Finally, the output embeddings in the last layer of each channel are concatenated and fed into a fully connected network for topic event recognition. Extensive experiments validate the effectiveness of our method, and the results confirm its superiority over state-of-the-art baselines. In-depth analyses explore the essential factors (e.g., graph structures, attentions, feature generation method, etc.) determining the extraction performance.
- Open Access
- 22 March 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (4) , 1-27
Token-Event-Role Structure-Based Multi-Channel Document-Level Event Extraction
Document-level event extraction is a long-standing challenging information retrieval problem involving a sequence of sub-tasks: entity extraction, event type judgment, and event type-specific multi-event extraction. However, addressing the problem as multiple learning tasks leads to increased model complexity. Also, existing methods insufficiently utilize the correlation of entities crossing different events, resulting in limited event extraction performance. This article introduces a novel framework for document-level event extraction, incorporating a new data structure called token-event-role and a multi-channel argument role prediction module. The proposed data structure enables our model to uncover the primary role of tokens in multiple events, facilitating a more comprehensive understanding of event relationships. By leveraging the multi-channel prediction module, we transform entity and multi-event extraction into a single task of predicting token–event pairs, thereby reducing the overall parameter size and enhancing model efficiency. The results demonstrate that our approach outperforms the state-of-the-art method by 9.5 percentage points in terms of the F 1 score, highlighting its superior performance in event extraction. Furthermore, an ablation study confirms the significant value of the proposed data structure in improving event extraction tasks, further validating its importance in enhancing the overall performance of the framework.
- 22 March 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (4) , 1-27
Open AccessToken-Event-Role Structure-Based Multi-Channel Document-Level Event Extraction
Document-level event extraction is a long-standing challenging information retrieval problem involving a sequence of sub-tasks: entity extraction, event type judgment, and event type-specific multi-event extraction. However, addressing the problem as multiple learning tasks leads to increased model complexity. Also, existing methods insufficiently utilize the correlation of entities crossing different events, resulting in limited event extraction performance. This article introduces a novel framework for document-level event extraction, incorporating a new data structure called token-event-role and a multi-channel argument role prediction module. The proposed data structure enables our model to uncover the primary role of tokens in multiple events, facilitating a more comprehensive understanding of event relationships. By leveraging the multi-channel prediction module, we transform entity and multi-event extraction into a single task of predicting token–event pairs, thereby reducing the overall parameter size and enhancing model efficiency. The results demonstrate that our approach outperforms the state-of-the-art method by 9.5 percentage points in terms of the F 1 score, highlighting its superior performance in event extraction. Furthermore, an ablation study confirms the significant value of the proposed data structure in improving event extraction tasks, further validating its importance in enhancing the overall performance of the framework.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 4446-4459
OEE-CFC: A Dataset for Open Event Extraction from Chinese Financial Commentary
Qizhi Wan, Changxuan Wan, Rong Hu, Dexi Liu, Xu Wenwu, Kang Xu, Zou Meihua, Liu Tao, Jie Yang, Zhenwei Xiong. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 4446-4459
Open AccessOEE-CFC: A Dataset for Open Event Extraction from Chinese Financial Commentary
Qizhi Wan, Changxuan Wan, Rong Hu, Dexi Liu, Xu Wenwu, Kang Xu, Zou Meihua, Liu Tao, Jie Yang, Zhenwei Xiong. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- Open Access
- 29 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (3) , 1-31
rHDP: An Aspect Sharing-Enhanced Hierarchical Topic Model for Multi-Domain Corpus
Learning topic hierarchies from a multi-domain corpus is crucial in topic modeling as it reveals valuable structural information embedded within documents. Despite the extensive literature on hierarchical topic models, effectively discovering inter-topic correlations and differences among subtopics at the same level in the topic hierarchy, obtained from multiple domains, remains an unresolved challenge. This article proposes an enhanced nested Chinese restaurant process (nCRP), nCRP+, by introducing an additional mechanism based on Chinese restaurant franchise (CRF) for aspect-sharing pattern extraction in the original nCRP. Subsequently, by employing the distribution extracted from nCRP+ as the prior distribution for topic hierarchy in the hierarchical Dirichlet processes (HDP), we develop a hierarchical topic model for multi-domain corpus, named rHDP. We describe the model with the analogy of Chinese restaurant franchise based on the central kitchen and propose a hierarchical Gibbs sampling scheme to infer the model. Our method effectively constructs well-established topic hierarchies, accurately reflecting diverse parent-child topic relationships, explicit topic aspect sharing correlations for inter-topics, and differences between these shared topics. To validate the efficacy of our approach, we conduct experiments using a renowned public dataset and an online collection of Chinese financial documents. The experimental results confirm the superiority of our method over the state-of-the-art techniques in identifying multi-domain topic hierarchies, according to multiple evaluation metrics.
- 29 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (3) , 1-31
Open AccessrHDP: An Aspect Sharing-Enhanced Hierarchical Topic Model for Multi-Domain Corpus
Learning topic hierarchies from a multi-domain corpus is crucial in topic modeling as it reveals valuable structural information embedded within documents. Despite the extensive literature on hierarchical topic models, effectively discovering inter-topic correlations and differences among subtopics at the same level in the topic hierarchy, obtained from multiple domains, remains an unresolved challenge. This article proposes an enhanced nested Chinese restaurant process (nCRP), nCRP+, by introducing an additional mechanism based on Chinese restaurant franchise (CRF) for aspect-sharing pattern extraction in the original nCRP. Subsequently, by employing the distribution extracted from nCRP+ as the prior distribution for topic hierarchy in the hierarchical Dirichlet processes (HDP), we develop a hierarchical topic model for multi-domain corpus, named rHDP. We describe the model with the analogy of Chinese restaurant franchise based on the central kitchen and propose a hierarchical Gibbs sampling scheme to infer the model. Our method effectively constructs well-established topic hierarchies, accurately reflecting diverse parent-child topic relationships, explicit topic aspect sharing correlations for inter-topics, and differences between these shared topics. To validate the efficacy of our approach, we conduct experiments using a renowned public dataset and an online collection of Chinese financial documents. The experimental results confirm the superiority of our method over the state-of-the-art techniques in identifying multi-domain topic hierarchies, according to multiple evaluation metrics.