Sorry, you need to enable JavaScript to visit this website.

NEW INTENT DISCOVERY WITH MULTI-VIEW CLUSTERING

DOI:
10.60864/xgwe-4687
Citation Author(s):
Submitted by:
Junjie Sun
Last updated:
6 June 2024 - 10:50am
Document Type:
Poster
 

New intent discovery aims to identify new intents from unlabeled utterances in the open-world scenario. As the fundamental and challenging problem in dialogue systems, new intent discovery attracts increasing attention but is still under exploration. In this paper, we propose a simple and effective new intent discovery framework with multi-view clustering. Specifically, we first adopt a double-branch representation learning strategy to learn high-quality utterance representations. Then we conduct a multi-view clustering method to obtain the satisfactory cluster assignment in an iterative manner, thus fulfilling the new intent discovery task. Extensive experimental results on three widely-used datasets demonstrate that our proposed method outperforms other strong baselines in most cases.

up
0 users have voted: