Diversifying Dialogue Generation with Non-Conversational Text

Hui Su, Xiaoyu Shen, Sanqiang Zhao, Zhou Xiao, Pengwei Hu, Randy Zhong, Cheng Niu, Jie Zhou


Abstract
Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation. As bland and generic utterances usually dominate the frequency distribution in our daily chitchat, avoiding them to generate more interesting responses requires complex data filtering, sampling techniques or modifying the training objective. In this paper, we propose a new perspective to diversify dialogue generation by leveraging non-conversational text. Compared with bilateral conversations, non-conversational text are easier to obtain, more diverse and cover a much broader range of topics. We collect a large-scale non-conversational corpus from multi sources including forum comments, idioms and book snippets. We further present a training paradigm to effectively incorporate these text via iterative back translation. The resulting model is tested on two conversational datasets from different domains and is shown to produce significantly more diverse responses without sacrificing the relevance with context.
Anthology ID:
2020.acl-main.634
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7087–7097
Language:
URL:
https://aclanthology.org/2020.acl-main.634
DOI:
10.18653/v1/2020.acl-main.634
Bibkey:
Cite (ACL):
Hui Su, Xiaoyu Shen, Sanqiang Zhao, Zhou Xiao, Pengwei Hu, Randy Zhong, Cheng Niu, and Jie Zhou. 2020. Diversifying Dialogue Generation with Non-Conversational Text. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7087–7097, Online. Association for Computational Linguistics.
Cite (Informal):
Diversifying Dialogue Generation with Non-Conversational Text (Su et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2020.acl-main.634.pdf
Video:
 http://slideslive.com/38929350
Code
 chin-gyou/Div-Non-Conv
Data
Douban