Multi-turn Response Selection using Dialogue Dependency Relations

Qi Jia, Yizhu Liu, Siyu Ren, Kenny Zhu, Haifeng Tang


Abstract
Multi-turn response selection is a task designed for developing dialogue agents. The performance on this task has a remarkable improvement with pre-trained language models. However, these models simply concatenate the turns in dialogue history as the input and largely ignore the dependencies between the turns. In this paper, we propose a dialogue extraction algorithm to transform a dialogue history into threads based on their dependency relations. Each thread can be regarded as a self-contained sub-dialogue. We also propose Thread-Encoder model to encode threads and candidates into compact representations by pre-trained Transformers and finally get the matching score through an attention layer. The experiments show that dependency relations are helpful for dialogue context understanding, and our model outperforms the state-of-the-art baselines on both DSTC7 and DSTC8*, with competitive results on UbuntuV2.
Anthology ID:
2020.emnlp-main.150
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1911–1920
Language:
URL:
https://aclanthology.org/2020.emnlp-main.150
DOI:
10.18653/v1/2020.emnlp-main.150
Bibkey:
Cite (ACL):
Qi Jia, Yizhu Liu, Siyu Ren, Kenny Zhu, and Haifeng Tang. 2020. Multi-turn Response Selection using Dialogue Dependency Relations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1911–1920, Online. Association for Computational Linguistics.
Cite (Informal):
Multi-turn Response Selection using Dialogue Dependency Relations (Jia et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.150.pdf
Video:
 https://slideslive.com/38938667
Code
 JiaQiSJTU/ResponseSelection