Discovering New Intents with Deep Aligned Clustering

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.

Accepted by AAAI 2021 (Main Track, Long Paper)

References in corpus (3)

• Multi-class Classification without Multi-class Labels
• Dialogue State Induction Using Neural Latent Variable Models
• Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement

Cited by in corpus (8)

• MIntRec: A New Dataset for Multimodal Intent Recognition
• Learning Discriminative Representations and Decision Boundaries for Open Intent Detection
• A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery
• OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision
• Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems
• Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling
• ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding
• One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning