Discovering New Intents with Deep Aligned Clustering

TL;DR

This paper introduces Deep Aligned Clustering, a novel approach for discovering new dialogue intents by leveraging limited known intent data, aligning cluster labels, and predicting the number of new intent categories, outperforming existing methods.

Contribution

The paper proposes a new deep clustering method that uses prior knowledge and label alignment to improve new intent discovery in dialogue systems.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively predicts the number of new intent categories.

Demonstrates robustness in discovering new intents with limited prior data.

Abstract

Discovering new intents is a crucial task in dialogue systems. Most existing methods are limited in transferring the prior knowledge from known intents to new intents. They also have difficulties in providing high-quality supervised signals to learn clustering-friendly features for grouping unlabeled intents. In this work, we propose an effective method, Deep Aligned Clustering, to discover new intents with the aid of the limited known intent data. Firstly, we leverage a few labeled known intent samples as prior knowledge to pre-train the model. Then, we perform k-means to produce cluster assignments as pseudo-labels. Moreover, we propose an alignment strategy to tackle the label inconsistency problem during clustering assignments. Finally, we learn the intent representations under the supervision of the aligned pseudo-labels. With an unknown number of new intents, we predict the number of intent categories by eliminating low-confidence intent-wise clusters. Extensive experiments on two benchmark datasets show that our method is more robust and achieves substantial improvements over the state-of-the-art methods. The codes are released at https://github.com/thuiar/DeepAligned-Clustering.