mlsanityData to 7 Oct 2026

Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts

arXiv 2305.03237 ↗First posted 5 May 2023cs.CL cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Out-of-Domain (OOD) intent detection is vital for practical dialogue systems, and it usually requires considering multi-turn dialogue contexts. However, most previous OOD intent detection approaches are limited to single dialogue turns. In this paper, we introduce a context-aware OOD intent detection (Caro) framework to model multi-turn contexts in OOD intent detection tasks. Specifically, we follow the information bottleneck principle to extract robust representations from multi-turn dialogue contexts. Two different views are constructed for each input sample and the superfluous information not related to intent detection is removed using a multi-view information bottleneck loss. Moreover, we also explore utilizing unlabeled data in Caro. A two-stage training process is introduced to mine OOD samples from these unlabeled data, and these OOD samples are used to train the resulting model with a bootstrapping approach. Comprehensive experiments demonstrate that Caro establishes state-of-the-art performances on multi-turn OOD detection tasks by improving the F1-OOD score of over 29% compared to the previous best method.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 59 of its 103 references that are in the map. First posted on arXiv 5 May 2023.

Builds on

59 of 103 references.

References · 59

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  11. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
38 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  2. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  3. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  4. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  5. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  6. 2019On Variational Bounds of Mutual Informationcited by 550
  7. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  8. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  9. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
  10. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  11. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  12. 2020Learning Robust Representations via Multi-View Information Bottleneckcited by 189
  13. 2021DialogSum: A Real-Life Scenario Dialogue Summarization Datasetcited by 181
  14. 2017A Survey on Dialogue Systems: Recent Advances and New Frontierscited by 162
  15. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  16. 2015Yara Parser: A Fast and Accurate Dependency Parsercited by 110
  17. 2017DOC: Deep Open Classification of Text Documentscited by 109
  18. 2022Training OOD Detectors in their Natural Habitatscited by 86
  19. 2022Self-Training: A Surveycited by 85
  20. 2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 70
  21. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  22. 2021Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detectioncited by 67
  23. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  24. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  25. 2020Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structurecited by 60
  26. 2020Deep Open Intent Classification with Adaptive Decision Boundarycited by 56
  27. 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
  28. 2020STAR: A Schema-Guided Dialog Dataset for Transfer Learningcited by 43
  29. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
  30. 2021Out-of-Scope Intent Detection with Self-Supervision and Discriminative Trainingcited by 42
  31. 2019Out-of-Domain Detection for Low-Resource Text Classification Taskscited by 36
  32. 2019Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialogcited by 33
  33. 2020Robustness Testing of Language Understanding in Task-Oriented Dialogcited by 32
  34. 2021Unsupervised Out-of-Domain Detection via Pre-trained Transformerscited by 31
  35. 2021TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognitioncited by 24
  36. 2021Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLUcited by 22
  37. 2021GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentationcited by 20
  38. 2018Neural Sentence Embedding using Only In-domain Sentences for Out-of-domain Sentence Detection in Dialog Systemscited by 18

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

6 papers.

  1. 2023Long-Tailed Question Answering in an Open Worldcited by 7
  2. 2023Domain Incremental Lifelong Learning in an Open Worldcited by 5
  3. 2026WASIL: In-the-Wild Arabic Spoken Interactions with LLMscited by 1
  4. 2024'No' Matters: Out-of-Distribution Detection in Multimodality Long Dialoguecited by 0
  5. 2025Beyond More Context: Retrieval Diversity Boosts Multi-Turn Intent Understandingcited by 0
  6. 2026Interpretability of the Intent Detection Problem: A New Approachcited by 0