Improving Multi-Party Dialogue Discourse Parsing via Domain Integration

Zhengyuan Liu, Nancy Chen


Abstract
While multi-party conversations are often less structured than monologues and documents, they are implicitly organized by semantic level correlations across the interactive turns, and dialogue discourse analysis can be applied to predict the dependency structure and relations between the elementary discourse units, and provide feature-rich structural information for downstream tasks. However, the existing corpora with dialogue discourse annotation are collected from specific domains with limited sample sizes, rendering the performance of data-driven approaches poor on incoming dialogues without any domain adaptation. In this paper, we first introduce a Transformer-based parser, and assess its cross-domain performance. We next adopt three methods to gain domain integration from both data and language modeling perspectives to improve the generalization capability. Empirical results show that the neural parser can benefit from our proposed methods, and performs better on cross-domain dialogue samples.
Anthology ID:
2021.codi-main.11
Volume:
Proceedings of the 2nd Workshop on Computational Approaches to Discourse
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic and Online
Venues:
CODI | CRAC | EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
122–127
Language:
URL:
https://aclanthology.org/2021.codi-main.11
DOI:
10.18653/v1/2021.codi-main.11
Bibkey:
Cite (ACL):
Zhengyuan Liu and Nancy Chen. 2021. Improving Multi-Party Dialogue Discourse Parsing via Domain Integration. In Proceedings of the 2nd Workshop on Computational Approaches to Discourse, pages 122–127, Punta Cana, Dominican Republic and Online. Association for Computational Linguistics.
Cite (Informal):
Improving Multi-Party Dialogue Discourse Parsing via Domain Integration (Liu & Chen, CODI 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.codi-main.11.pdf
Code
 seq-to-mind/DDP_parsing
Data
Molweni