CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling

Han Wu, Kun Xu, Linqi Song


Abstract
Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to handle conversational structural information. In this paper, we present a simple and effective architecture for CSRL which aims to address this problem. Our model is based on a conversational structure aware graph network which explicitly encodes the speaker dependent information. We also propose a multi-task learning method to further improve the model. Experimental results on benchmark datasets show that our model with our proposed training objectives significantly outperforms previous baselines.
Anthology ID:
2021.emnlp-main.177
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2312–2317
Language:
URL:
https://aclanthology.org/2021.emnlp-main.177
DOI:
10.18653/v1/2021.emnlp-main.177
Bibkey:
Cite (ACL):
Han Wu, Kun Xu, and Linqi Song. 2021. CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2312–2317, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling (Wu et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.177.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.177.mp4
Code
 hahahawu/CSAGN