KULCQ: An Unsupervised Keyword-based Utterance Level Clustering Quality Metric

TL;DR

KULCQ is an unsupervised metric that evaluates conversational utterance clustering quality by analyzing keywords, effectively capturing semantic nuances without requiring labeled intent data.

Contribution

The paper introduces KULCQ, a novel keyword-based unsupervised metric for assessing utterance clustering quality in conversational data, addressing limitations of existing metrics.

Findings

KULCQ outperforms existing unsupervised metrics in capturing semantic relationships.

KULCQ maintains consistency with geometric clustering principles.

Ablation studies validate KULCQ's effectiveness.

Abstract

Intent discovery is crucial for both building new conversational agents and improving existing ones. While several approaches have been proposed for intent discovery, most rely on clustering to group similar utterances together. Traditional evaluation of these utterance clusters requires intent labels for each utterance, limiting scalability. Although some clustering quality metrics exist that do not require labeled data, they focus solely on cluster geometry while ignoring the linguistic nuances present in conversational transcripts. In this paper, we introduce Keyword-based Utterance Level Clustering Quality (KULCQ), an unsupervised metric that leverages keyword analysis to evaluate clustering quality. We demonstrate KULCQ's effectiveness by comparing it with existing unsupervised clustering metrics and validate its performance through comprehensive ablation studies. Our results show that KULCQ better captures semantic relationships in conversational data while maintaining consistency with geometric clustering principles.