DMIN: A Discourse-specific Multi-granularity Integration Network for Conversational Aspect-based Sentiment Quadruple Analysis

Peijie Huang, Xisheng Xiao, Yuhong Xu, Jiawei Chen


Abstract
Conversational Aspect-based Sentiment Quadruple Analysis (DiaASQ) aims to extract fine-grained sentiment quadruples from dialogues. Previous research has primarily concentrated on enhancing token-level interactions, still lacking in sufficient modeling of the discourse structure information in dialogue. Firstly, it does not incorporate interactions among different utterances in the encoding stage, resulting in a limited token-level context understanding for subsequent modules. Secondly, it ignores the critical fact that discourse information is naturally organized at the utterance level and learning it solely at the token level is incomplete. In this work, we strengthen the token-level encoder by utilizing a discourse structure called “thread” and graph convolutional networks to enhance the token interaction among different utterances. Moreover, we propose an utterance-level encoder to learn the structured speaker and reply information, providing a macro understanding of dialogue discourse. Furthermore, we introduce a novel Multi-granularities Integrator to integrate token-level and utterance-level representations, resulting in a comprehensive and cohesive dialogue contextual understanding. Experiments on two datasets demonstrate that our model achieves state-of-the-art performance. Our codes are publicly available at https://github.com/SIGSDSscau/DMIN.
Anthology ID:
2024.findings-acl.966
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16326–16338
Language:
URL:
https://aclanthology.org/2024.findings-acl.966
DOI:
10.18653/v1/2024.findings-acl.966
Bibkey:
Cite (ACL):
Peijie Huang, Xisheng Xiao, Yuhong Xu, and Jiawei Chen. 2024. DMIN: A Discourse-specific Multi-granularity Integration Network for Conversational Aspect-based Sentiment Quadruple Analysis. In Findings of the Association for Computational Linguistics: ACL 2024, pages 16326–16338, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
DMIN: A Discourse-specific Multi-granularity Integration Network for Conversational Aspect-based Sentiment Quadruple Analysis (Huang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.966.pdf