mlsanityData to 7 Oct 2026

Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery

arXiv 2410.20219 ↗First posted 26 Oct 2024cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

New intent discovery is a crucial capability for task-oriented dialogue systems. Existing methods focus on transferring in-domain (IND) prior knowledge to out-of-domain (OOD) data through pre-training and clustering stages. They either handle the two processes in a pipeline manner, which exhibits a gap between intent representation and clustering process or use typical contrastive clustering that overlooks the potential supervised signals from the whole data. Besides, they often individually deal with open intent discovery or OOD settings. To this end, we propose a Pseudo-Label enhanced Prototypical Contrastive Learning (PLPCL) model for uniformed intent discovery. We iteratively utilize pseudo-labels to explore potential positive/negative samples for contrastive learning and bridge the gap between representation and clustering. To enable better knowledge transfer, we design a prototype learning method integrating the supervised and pseudo signals from IND and OOD samples. In addition, our method has been proven effective in two different settings of discovering new intents. Experiments on three benchmark datasets and two task settings demonstrate the effectiveness of our approach.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 49 references that are in the map. First posted on arXiv 26 Oct 2024.

Builds on

29 of 49 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
  4. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
  5. 2020Contrastive Clusteringcited by 264
  6. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  7. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  8. 2017Learning to cluster in order to transfer across domains and taskscited by 128
  9. 2019A continual learning survey: Defying forgetting in classification taskscited by 118
  10. 2019Multi-class Classification without Multi-class Labelscited by 100
  11. 2020Discovering New Intents with Deep Aligned Clusteringcited by 68
  12. 2021Learning Representation for Clustering via Prototype Scattering and Positive Samplingcited by 58
17 more
  1. 2019Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinementcited by 56
  2. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
  3. 2022Generalized Category Discovery with Decoupled Prototypical Networkcited by 35
  4. 2022New Intent Discovery with Pre-training and Contrastive Learningcited by 28
  5. 2022Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embeddingcited by 28
  6. 2020Intent Mining from past conversations for conversational agentcited by 25
  7. 2021TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognitioncited by 24
  8. 2023Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPTcited by 16
  9. 2023Generalized Category Discovery with Large Language Models in the Loopcited by 15
  10. 2019Towards Open Intent Discovery for Conversational Textcited by 13
  11. 2022Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learningcited by 13
  12. 2020Dialogue State Induction Using Neural Latent Variable Modelscited by 10
  13. 2022Generalized Intent Discovery: Learning from Open World Dialogue Systemcited by 10
  14. 2021Open Intent Discovery through Unsupervised Semantic Clustering and Dependency Parsingcited by 9
  15. 2021An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Fillingcited by 9
  16. 2022Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discoverycited by 9
  17. 2024Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discoverycited by 9

Built on by

Not cited yet.