Dialogue Response Selection with Hierarchical Curriculum Learning
Yixuan Su, Deng Cai, Qingyu Zhou, Zibo Lin, Simon Baker, Yunbo Cao, Shuming Shi, Nigel Collier
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.
BibTeX
@inproceedings{su-etal-2021-dialogue,
title = "Dialogue Response Selection with Hierarchical Curriculum Learning",
author = "Su, Yixuan and
Cai, Deng and
Zhou, Qingyu and
Lin, Zibo and
Baker, Simon and
Cao, Yunbo and
Shi, Shuming and
Collier, Nigel and
Wang, Yan",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "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 = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.137/",
doi = "10.18653/v1/2021.acl-long.137",
pages = "1740--1751"
}