mlsanityData to 7 Oct 2026

Generalized Intent Discovery: Learning from Open World Dialogue System

arXiv 2209.06030 ↗First posted 13 Sep 2022cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Traditional intent classification models are based on a pre-defined intent set and only recognize limited in-domain (IND) intent classes. But users may input out-of-domain (OOD) queries in a practical dialogue system. Such OOD queries can provide directions for future improvement. In this paper, we define a new task, Generalized Intent Discovery (GID), which aims to extend an IND intent classifier to an open-world intent set including IND and OOD intents. We hope to simultaneously classify a set of labeled IND intent classes while discovering and recognizing new unlabeled OOD types incrementally. We construct three public datasets for different application scenarios and propose two kinds of frameworks, pipeline-based and end-to-end for future work. Further, we conduct exhaustive experiments and qualitative analysis to comprehend key challenges and provide new guidance for future GID research.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 23 of its 45 references that are in the map. First posted on arXiv 13 Sep 2022.

Builds on

23 of 45 references.

References · 23

  1. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  4. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  5. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  6. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  7. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
  8. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
  9. 2019BERT for Joint Intent Classification and Slot Fillingcited by 195
  10. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  11. 2021A Unified Objective for Novel Class Discoverycited by 161
  12. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 141
11 more
  1. 2016Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Fillingcited by 137
  2. 2019A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understandingcited by 106
  3. 2019A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Fillingcited by 85
  4. 2020Discovering New Intents with Deep Aligned Clusteringcited by 68
  5. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  6. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  7. 2019Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinementcited by 56
  8. 2020Deep Open Intent Classification with Adaptive Decision Boundarycited by 56
  9. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
  10. 2018Open-world Learning and Application to Product Classificationcited by 39
  11. 2021Generalized Zero-shot Intent Detection via Commonsense Knowledgecited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 2; 2026: 1.

10 papers.

  1. 2023Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPTcited by 16
  2. 2023A Diffusion Weighted Graph Framework for New Intent Discoverycited by 7
  3. 2023Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discoverycited by 5
  4. 2023Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognitioncited by 5
  5. 2024Domain Adaptation in Intent Classification Systems: A Reviewcited by 4
  6. 2024Towards Real-world Scenario: Imbalanced New Intent Discoverycited by 2
  7. 2025Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Frameworkcited by 2
  8. 2024Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discoverycited by 0
  9. 2025NILC: Discovering New Intents with LLM-assisted Clusteringcited by 0
  10. 2026Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Spacecited by 0