Semi-supervised new slot discovery with incremental clustering
Publication Type
Conference Proceeding Article
Publication Date
12-2022
Abstract
Discovering new slots is critical to the success of dialogue systems. Most existing methods rely on automatic slot induction in an unsupervised fashion or perform domain adaptation across zero or few-shot scenarios. They have difficulties in providing high-quality supervised signals to learn clustering-friendly features, and are limited in effectively transferring the prior knowledge from known slots to new slots. In this work, we propose a Semi-supervised Incremental Clustering method (SIC), to discover new slots with the aid of existing linguistic annotation models and limited known slot data. Specifically, we harvest slot value candidates with NLP model cues and innovatively formulate the slot discovery task under an incremental clustering framework. The model gradually calibrates slot representations under the supervision of generated pseudo-labels, and automatically learns to terminate when no more salient slot remains. Our thorough evaluation on five public datasets demonstrates that the proposed method significantly outperforms state-of-theart models.
Keywords
Incremental data, Incremental cluster
Discipline
Artificial Intelligence and Robotics
Research Areas
Data Science and Engineering; Intelligent Systems and Optimization
Publication
Findings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, 2022 December 7 -11
Publisher
Association for Computational Linguistics
City or Country
Stroudsburg, Pennsylvania, United States
Citation
WU, Yuxia; LIAO, Lizi; QIAN, Xuemin; and CHUA, Tat-Seng.
Semi-supervised new slot discovery with incremental clustering. (2022). Findings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, 2022 December 7 -11.
Available at: https://ink.library.smu.edu.sg/sis_research/7736