mlsanityData to 7 Oct 2026

A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery

arXiv 2303.04134 ↗First posted 7 Mar 2023cs.CL cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Intent Detection is one of the tasks of the Natural Language Understanding (NLU) unit in task-oriented dialogue systems. Out of Scope (OOS) and Out of Domain (OOD) inputs may run these systems into a problem. On the other side, a labeled dataset is needed to train a model for Intent Detection in task-oriented dialogue systems. The creation of a labeled dataset is time-consuming and needs human resources. The purpose of this article is to address mentioned problems. The task of identifying OOD/OOS inputs is named OOD/OOS Intent Detection. Also, discovering new intents and pseudo-labeling of OOD inputs is well known by Intent Discovery. In OOD intent detection part, we make use of a Variational Autoencoder to distinguish between known and unknown intents independent of input data distribution. After that, an unsupervised clustering method is used to discover different unknown intents underlying OOD/OOS inputs. We also apply a non-linear dimensionality reduction on OOD/OOS representations to make distances between representations more meaning full for clustering. Our results show that the proposed model for both OOD/OOS Intent Detection and Intent Discovery achieves great results and passes baselines in English and Persian languages.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 32 of its 66 references that are in the map. First posted on arXiv 7 Mar 2023.

Builds on

32 of 66 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  3. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  4. 2016Bag of Tricks for Efficient Text Classificationcited by 869
  5. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  6. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  7. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  8. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  9. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  10. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  11. 2023Non-Parametric Outlier Synthesiscited by 129
  12. 2017DOC: Deep Open Classification of Text Documentscited by 109
20 more
  1. 2020ParsBERT: Transformer-based Model for Persian Language Understandingcited by 92
  2. 2020Discovering New Intents with Deep Aligned Clusteringcited by 68
  3. 2021Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detectioncited by 67
  4. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  5. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  6. 2022Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detectioncited by 59
  7. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpaintingcited by 57
  8. 2020Deep Open Intent Classification with Adaptive Decision Boundarycited by 56
  9. 2018Zero-shot User Intent Detection via Capsule Neural Networkscited by 54
  10. 2019Out-of-distribution Detection in Classifiers via Generationcited by 49
  11. 2023Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Needcited by 46
  12. 2021Out-of-Scope Intent Detection with Self-Supervision and Discriminative Trainingcited by 42
  13. 2022Out-of-Distribution Detection with Semantic Mismatch under Maskingcited by 22
  14. 2021OodGAN: Generative Adversarial Network for Out-of-Domain Data Generationcited by 15
  15. 2022Towards Textual Out-of-Domain Detection without In-Domain Labelscited by 14
  16. 2021Automatic Intent-Slot Induction for Dialogue Systemscited by 13
  17. 2019CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbotscited by 10
  18. 2016Constraint-Based Clustering Selectioncited by 6
  19. 2023Uncertainty-Estimation with Normalized Logits for Out-of-Distribution Detectioncited by 4
  20. 2023A Persian Benchmark for Joint Intent Detection and Slot Fillingcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  2. 2023BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detectioncited by 0