Log In Sign Up

Group-wise Contrastive Learning for Neural Dialogue Generation

by   Hengyi Cai, et al.

Neural dialogue response generation has gained much popularity in recent years. Maximum Likelihood Estimation (MLE) objective is widely adopted in existing dialogue model learning. However, models trained with MLE objective function are plagued by the low-diversity issue when it comes to the open-domain conversational setting. Inspired by the observation that humans not only learn from the positive signals but also benefit from correcting behaviors of undesirable actions, in this work, we introduce contrastive learning into dialogue generation, where the model explicitly perceives the difference between the well-chosen positive and negative utterances. Specifically, we employ a pretrained baseline model as a reference. During contrastive learning, the target dialogue model is trained to give higher conditional probabilities for the positive samples, and lower conditional probabilities for those negative samples, compared to the reference model. To manage the multi-mapping relations prevailed in human conversation, we augment contrastive dialogue learning with group-wise dual sampling. Extensive experimental results show that the proposed group-wise contrastive learning framework is suited for training a wide range of neural dialogue generation models with very favorable performance over the baseline training approaches.


page 1

page 2

page 3

page 4


Two-Level Supervised Contrastive Learning for Response Selection in Multi-Turn Dialogue

Selecting an appropriate response from many candidates given the utteran...

Negative Training for Neural Dialogue Response Generation

Although deep learning models have brought tremendous advancements to th...

The CRINGE Loss: Learning what language not to model

Standard language model training employs gold human documents or human-h...

Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization

Being able to reply with a related, fluent, and informative response is ...

Multi-Referenced Training for Dialogue Response Generation

In open-domain dialogue response generation, a dialogue context can be c...

Generative Visual Dialogue System via Adaptive Reasoning and Weighted Likelihood Estimation

The key challenge of generative Visual Dialogue (VD) systems is to respo...

Conditional Generation and Snapshot Learning in Neural Dialogue Systems

Recently a variety of LSTM-based conditional language models (LM) have b...

Code Repositories


The codebase for "Group-wise Contrastive Learning for Neural Dialogue Generation" (Cai et al., EMNLP 2020)

view repo