Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement
This work addresses the challenge of intent discovery in dialogue systems, which is incremental as it builds on existing clustering methods by adding constraints and refinement to improve robustness and reduce sensitivity to cluster numbers.
The paper tackles the problem of identifying new user intents in dialogue systems by proposing CDAC+, an end-to-end clustering method that incorporates pairwise constraints as prior knowledge and refines clusters based on high-confidence assignments, resulting in significant improvements over strong baselines on three benchmark datasets.
Identifying new user intents is an essential task in the dialogue system. However, it is hard to get satisfying clustering results since the definition of intents is strongly guided by prior knowledge. Existing methods incorporate prior knowledge by intensive feature engineering, which not only leads to overfitting but also makes it sensitive to the number of clusters. In this paper, we propose constrained deep adaptive clustering with cluster refinement (CDAC+), an end-to-end clustering method that can naturally incorporate pairwise constraints as prior knowledge to guide the clustering process. Moreover, we refine the clusters by forcing the model to learn from the high confidence assignments. After eliminating low confidence assignments, our approach is surprisingly insensitive to the number of clusters. Experimental results on the three benchmark datasets show that our method can yield significant improvements over strong baselines.