Dialogue Response Selection with Hierarchical Curriculum Learning

by   Yixuan Su, et al.

We study the learning of a matching model for dialogue response selection. Motivated by the recent finding that random negatives are often too trivial to train a reliable model, we propose a hierarchical curriculum learning (HCL) framework that 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 response. On the other hand, IC progressively strengthens the model's ability in identifying the mismatched information between the dialogue context and response. Empirical studies on two benchmark datasets with three state-of-the-art matching models demonstrate that the proposed HCL significantly improves the model performance across various evaluation metrics.


page 1

page 2

page 3

page 4


Grayscale Data Construction and Multi-Level Ranking Objective for Dialogue Response Selection

Response selection plays a vital role in building retrieval-based conver...

Automatic Curriculum Learning With Over-repetition Penalty for Dialogue Policy Learning

Dialogue policy learning based on reinforcement learning is difficult to...

Hierarchical Curriculum Learning for AMR Parsing

Abstract Meaning Representation (AMR) parsing translates sentences to th...

Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems

We study learning of a matching model for response selection in retrieva...

Feeding What You Need by Understanding What You Learned

Machine Reading Comprehension (MRC) reveals the ability to understand a ...

PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation

Curriculum Data Augmentation (CDA) improves neural models by presenting ...

Please sign up or login with your details

Forgot password? Click here to reset