Learning Dialogue Representations from Consecutive Utterances

TL;DR

This paper introduces Dialogue Sentence Embedding (DSE), a self-supervised contrastive learning method that learns effective dialogue representations from consecutive utterances, significantly improving performance on various dialogue tasks especially in few-shot and zero-shot scenarios.

Contribution

The paper proposes DSE, a simple yet effective contrastive learning approach that leverages consecutive dialogue utterances to learn high-quality dialogue representations.

Findings

DSE outperforms existing dialogue representation models.

Achieves 13% average improvement in 1-shot intent classification.

Effective in few-shot and zero-shot dialogue tasks.

Abstract

Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence Embedding (DSE), a self-supervised contrastive learning method that learns effective dialogue representations suitable for a wide range of dialogue tasks. DSE learns from dialogues by taking consecutive utterances of the same dialogue as positive pairs for contrastive learning. Despite its simplicity, DSE achieves significantly better representation capability than other dialogue representation and universal sentence representation models. We evaluate DSE on five downstream dialogue tasks that examine dialogue representation at different semantic granularities. Experiments in few-shot and zero-shot settings show that DSE outperforms baselines by a large margin. For example, it achieves 13% average performance improvement over the strongest unsupervised baseline in 1-shot intent classification on 6 datasets. We also provide analyses on the benefits and limitations of our model.