Fine-grained Post-training for Improving Retrieval-based Dialogue Systems

Janghoon Han, Taesuk Hong, Byoungjae Kim, Youngjoong Ko, Jungyun Seo


Abstract
Retrieval-based dialogue systems display an outstanding performance when pre-trained language models are used, which includes bidirectional encoder representations from transformers (BERT). During the multi-turn response selection, BERT focuses on training the relationship between the context with multiple utterances and the response. However, this method of training is insufficient when considering the relations between each utterance in the context. This leads to a problem of not completely understanding the context flow that is required to select a response. To address this issue, we propose a new fine-grained post-training method that reflects the characteristics of the multi-turn dialogue. Specifically, the model learns the utterance level interactions by training every short context-response pair in a dialogue session. Furthermore, by using a new training objective, the utterance relevance classification, the model understands the semantic relevance and coherence between the dialogue utterances. Experimental results show that our model achieves new state-of-the-art with significant margins on three benchmark datasets. This suggests that the fine-grained post-training method is highly effective for the response selection task.
Anthology ID:
2021.naacl-main.122
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1549–1558
Language:
URL:
https://aclanthology.org/2021.naacl-main.122
DOI:
10.18653/v1/2021.naacl-main.122
Bibkey:
Cite (ACL):
Janghoon Han, Taesuk Hong, Byoungjae Kim, Youngjoong Ko, and Jungyun Seo. 2021. Fine-grained Post-training for Improving Retrieval-based Dialogue Systems. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1549–1558, Online. Association for Computational Linguistics.
Cite (Informal):
Fine-grained Post-training for Improving Retrieval-based Dialogue Systems (Han et al., NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2021.naacl-main.122.pdf
Optional supplementary code:
 2021.naacl-main.122.OptionalSupplementaryCode.zip
Optional supplementary data:
 2021.naacl-main.122.OptionalSupplementaryData.zip
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2021.naacl-main.122.mp4
Data
DoubanE-commerceRRSRRS Ranking TestUDC