A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing

Yaxin Fan, Peifeng Li, Fang Kong, Qiaoming Zhu


Abstract
Conversational discourse parsing aims to construct an implicit utterance dependency tree to reflect the turn-taking in a multi-party conversation. Existing works are generally divided into two lines: graph-based and transition-based paradigms, which perform well for short-distance and long-distance dependency links, respectively. However, there is no study to consider the advantages of both paradigms to facilitate conversational discourse parsing. As a result, we propose a distance-aware multi-task framework DAMT that incorporates the strengths of transition-based paradigm to facilitate the graph-based paradigm from the encoding and decoding process. To promote multi-task learning on two paradigms, we first introduce an Encoding Interactive Module (EIM) to enhance the flow of semantic information between both two paradigms during the encoding step. And then we apply a Distance-Aware Graph Convolutional Network (DAGCN) in the decoding process, which can incorporate the different-distance dependency links predicted by the transition-based paradigm to facilitate the decoding of the graph-based paradigm. The experimental results on the datasets STAC and Molweni show that our method can significantly improve the performance of the SOTA graph-based paradigm on long-distance dependency links.
Anthology ID:
2022.coling-1.76
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
912–921
Language:
URL:
https://aclanthology.org/2022.coling-1.76
DOI:
Bibkey:
Cite (ACL):
Yaxin Fan, Peifeng Li, Fang Kong, and Qiaoming Zhu. 2022. A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 912–921, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing (Fan et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.76.pdf