Discovering New Intents with Deep Aligned Clustering

Authors

  • Hanlei Zhang State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University Beijing National Research Center for Information Science and Technology (BNRist)
  • Hua Xu State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University Beijing National Research Center for Information Science and Technology (BNRist)
  • Ting-En Lin State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University Beijing National Research Center for Information Science and Technology (BNRist)
  • Rui Lyu State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University Beijing University of Posts and Telecommunications University

Keywords:

Conversational AI/Dialog Systems, (Deep) Neural Network Algorithms, Clustering, Unsupervised & Self-Supervised Learning

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. These methods 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 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.

Downloads

Published

2021-05-18

How to Cite

Zhang, H., Xu, H., Lin, T.-E., & Lyu, R. (2021). Discovering New Intents with Deep Aligned Clustering. Proceedings of the AAAI Conference on Artificial Intelligence, 35(16), 14365-14373. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17689

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing III