Dialogue Response Selection with Hierarchical Curriculum Learning
This work aims to improve the robustness of dialogue response selection models for real-world applications by addressing the limitations of training with random negative samples.
This paper addresses the problem of dialogue response selection by proposing a hierarchical curriculum learning framework. This framework, composed of corpus-level and instance-level curricula, trains matching models in an easy-to-difficult scheme, leading to significant performance improvements on three benchmark datasets with three state-of-the-art models.
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.