Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue

TL;DR

This paper introduces a contrastive and multi-task learning approach for incomplete utterance rewriting in multi-turn dialogues, improving context understanding and intent consistency, and achieving state-of-the-art results.

Contribution

It proposes a novel joint modeling method using contrastive and multi-task learning to enhance utterance rewriting accuracy in dialogue systems.

Findings

Achieves state-of-the-art performance on public datasets.

Effectively captures semantics at sentence and token levels.

Improves intent consistency detection.

Abstract

Context modeling plays a significant role in building multi-turn dialogue systems. In order to make full use of context information, systems can use Incomplete Utterance Rewriting(IUR) methods to simplify the multi-turn dialogue into single-turn by merging current utterance and context information into a self-contained utterance. However, previous approaches ignore the intent consistency between the original query and rewritten query. The detection of omitted or coreferred locations in the original query can be further improved. In this paper, we introduce contrastive learning and multi-task learning to jointly model the problem. Our method benefits from carefully designed self-supervised objectives, which act as auxiliary tasks to capture semantics at both sentence-level and token-level. The experiments show that our proposed model achieves state-of-the-art performance on several public datasets.