Dialogue Response Selection with Hierarchical Curriculum Learning

Yixuan Su, Deng Cai, Qingyu Zhou, Zibo Lin, Simon Baker, Yunbo Cao, Shuming Shi, Nigel Collier, Yan Wang


Abstract
We study the learning of a matching model for dialogue response selection. Motivated by the recent finding that models trained with random negative samples are not ideal in real-world scenarios, we propose a hierarchical curriculum learning framework that trains the matching model in an “easy-to-difficult” scheme. Our learning framework consists of two complementary curricula: (1) corpus-level curriculum (CC); and (2) instance-level curriculum (IC). In CC, the model gradually increases its ability in finding the matching clues between the dialogue context and a response candidate. As for IC, it progressively strengthens the model’s ability in identifying the mismatching information between the dialogue context and a response candidate. Empirical studies on three benchmark datasets with three state-of-the-art matching models demonstrate that the proposed learning framework significantly improves the model performance across various evaluation metrics.
Anthology ID:
2021.acl-long.137
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:
1740–1751
Language:
URL:
https://aclanthology.org/2021.acl-long.137
DOI:
10.18653/v1/2021.acl-long.137
Bibkey:
Cite (ACL):
Yixuan Su, Deng Cai, Qingyu Zhou, Zibo Lin, Simon Baker, Yunbo Cao, Shuming Shi, Nigel Collier, and Yan Wang. 2021. Dialogue Response Selection with Hierarchical Curriculum Learning. In 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), pages 1740–1751, Online. Association for Computational Linguistics.
Cite (Informal):
Dialogue Response Selection with Hierarchical Curriculum Learning (Su et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/2021.acl-long.137.pdf
Video:
 https://preview.aclanthology.org/paclic-22-ingestion/2021.acl-long.137.mp4
Code
 yxuansu/HCL
Data
DoubanE-commerceRRS