Semantic Representation for Dialogue Modeling

Xuefeng Bai, Yulong Chen, Linfeng Song, Yue Zhang


Abstract
Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities. To this end, we exploit Abstract Meaning Representation (AMR) to help dialogue modeling. Compared with the textual input, AMR explicitly provides core semantic knowledge and reduces data sparsity. We develop an algorithm to construct dialogue-level AMR graphs from sentence-level AMRs and explore two ways to incorporate AMRs into dialogue systems. Experimental results on both dialogue understanding and response generation tasks show the superiority of our model. To our knowledge, we are the first to leverage a formal semantic representation into neural dialogue modeling.
Anthology ID:
2021.acl-long.342
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4430–4445
Language:
URL:
https://aclanthology.org/2021.acl-long.342
DOI:
10.18653/v1/2021.acl-long.342
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.342.pdf
Code
 muyeby/AMR-Dialogue
Data
DailyDialogDialogRE