Profile Consistency Identification for Open-domain Dialogue Agents

Haoyu Song, Yan Wang, Wei-Nan Zhang, Zhengyu Zhao, Ting Liu, Xiaojiang Liu


Abstract
Maintaining a consistent attribute profile is crucial for dialogue agents to naturally converse with humans. Existing studies on improving attribute consistency mainly explored how to incorporate attribute information in the responses, but few efforts have been made to identify the consistency relations between response and attribute profile. To facilitate the study of profile consistency identification, we create a large-scale human-annotated dataset with over 110K single-turn conversations and their key-value attribute profiles. Explicit relation between response and profile is manually labeled. We also propose a key-value structure information enriched BERT model to identify the profile consistency, and it gained improvements over strong baselines. Further evaluations on downstream tasks demonstrate that the profile consistency identification model is conducive for improving dialogue consistency.
Anthology ID:
2020.emnlp-main.539
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6651–6662
Language:
URL:
https://aclanthology.org/2020.emnlp-main.539
DOI:
10.18653/v1/2020.emnlp-main.539
Bibkey:
Cite (ACL):
Haoyu Song, Yan Wang, Wei-Nan Zhang, Zhengyu Zhao, Ting Liu, and Xiaojiang Liu. 2020. Profile Consistency Identification for Open-domain Dialogue Agents. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6651–6662, Online. Association for Computational Linguistics.
Cite (Informal):
Profile Consistency Identification for Open-domain Dialogue Agents (Song et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.539.pdf
Video:
 https://slideslive.com/38938821
Code
 songhaoyu/KvPI
Data
PersonalDialog