Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery

TL;DR

This paper introduces PLPCL, a novel method that enhances intent discovery in dialogue systems by using pseudo-labels and prototype learning to improve clustering and representation of both known and unknown intents.

Contribution

The paper proposes a pseudo-label enhanced prototypical contrastive learning approach that effectively bridges representation and clustering for uniformed intent discovery.

Findings

Effective in discovering new intents across different settings

Improves intent clustering accuracy on benchmark datasets

Bridges gap between intent representation and clustering process

Abstract

New intent discovery is a crucial capability for task-oriented dialogue systems. Existing methods focus on transferring in-domain (IND) prior knowledge to out-of-domain (OOD) data through pre-training and clustering stages. They either handle the two processes in a pipeline manner, which exhibits a gap between intent representation and clustering process or use typical contrastive clustering that overlooks the potential supervised signals from the whole data. Besides, they often individually deal with open intent discovery or OOD settings. To this end, we propose a Pseudo-Label enhanced Prototypical Contrastive Learning (PLPCL) model for uniformed intent discovery. We iteratively utilize pseudo-labels to explore potential positive/negative samples for contrastive learning and bridge the gap between representation and clustering. To enable better knowledge transfer, we design a prototype learning method integrating the supervised and pseudo signals from IND and OOD samples. In addition, our method has been proven effective in two different settings of discovering new intents. Experiments on three benchmark datasets and two task settings demonstrate the effectiveness of our approach.