mlsanityData to 7 Oct 2026

Energy-based Unknown Intent Detection with Data Manipulation

arXiv 2107.12542 ↗First posted 27 Jul 2021cs.CL cs.SD eess.AScited by 6

Not on the map. Why?

Abstract (arXiv)

Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set. In this paper, we propose using energy scores for this task as the energy score is theoretically aligned with the density of the input and can be derived from any classifier. However, high-quality OOD utterances are required during the training stage in order to shape the energy gap between OOD and in-distribution (IND), and these utterances are difficult to collect in practice. To tackle this problem, we propose a data manipulation framework to Generate high-quality OOD utterances with importance weighTs (GOT). Experimental results show that the energy-based detector fine-tuned by GOT can achieve state-of-the-art results on two benchmark datasets.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 27 Jul 2021.

Builds on

20 of 34 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  3. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  6. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  7. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  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. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  11. 2018Additive Margin Softmax for Face Verificationcited by 275
  12. 2017Multiplicative Normalizing Flows for Variational Bayesian Neural Networkscited by 157
8 more
  1. 2017DOC: Deep Open Classification of Text Documentscited by 109
  2. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  3. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  4. 2020Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweightcited by 34
  5. 2019Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialogcited by 33
  6. 2017Generative and Discriminative Text Classification with Recurrent Neural Networkscited by 30
  7. 2019Less Is Better: Unweighted Data Subsampling via Influence Functioncited by 30
  8. 2018Neural Sentence Embedding using Only In-domain Sentences for Out-of-domain Sentence Detection in Dialog Systemscited by 18

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2; 2024: 1.

6 papers.

  1. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  2. 2022Estimating Soft Labels for Out-of-Domain Intent Detectioncited by 11
  3. 2022UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learningcited by 5
  4. 2023SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rankcited by 3
  5. 2022Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)cited by 0
  6. 2024One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learningcited by 0