%0 Conference Proceedings %T Dialogue Response Selection with Hierarchical Curriculum Learning %A Su, Yixuan %A Cai, Deng %A Zhou, Qingyu %A Lin, Zibo %A Baker, Simon %A Cao, Yunbo %A Shi, Shuming %A Collier, Nigel %A Wang, Yan %Y Zong, Chengqing %Y Xia, Fei %Y Li, Wenjie %Y Navigli, Roberto %S 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) %D 2021 %8 August %I Association for Computational Linguistics %C Online %F su-etal-2021-dialogue %X 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. %R 10.18653/v1/2021.acl-long.137 %U https://aclanthology.org/2021.acl-long.137 %U https://doi.org/10.18653/v1/2021.acl-long.137 %P 1740-1751