# Energy-based Unknown Intent Detection with Data Manipulation

arXiv: https://arxiv.org/abs/2107.12542 · HTML: https://mlsanity.com/paper/2107.12542/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 27 Jul 2021.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One](https://mlsanity.com/paper/1912.03263/) (2019)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces](https://mlsanity.com/paper/1805.10190/) (2018)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [Multiplicative Normalizing Flows for Variational Bayesian Neural Networks](https://mlsanity.com/paper/1703.01961/) (2017)
- [DOC: Deep Open Classification of Text Documents](https://mlsanity.com/paper/1709.08716/) (2017)
- [Deep Unknown Intent Detection with Margin Loss](https://mlsanity.com/paper/1906.00434/) (2019)
- [Out-of-domain Detection for Natural Language Understanding in Dialog Systems](https://mlsanity.com/paper/1909.03862/) (2019)
- [Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight](https://mlsanity.com/paper/2004.02594/) (2020)
- [Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialog](https://mlsanity.com/paper/1912.12800/) (2019)
- [Generative and Discriminative Text Classification with Recurrent Neural Networks](https://mlsanity.com/paper/1703.01898/) (2017)
- [Less Is Better: Unweighted Data Subsampling via Influence Function](https://mlsanity.com/paper/1912.01321/) (2019)
- [Neural Sentence Embedding using Only In-domain Sentences for Out-of-domain Sentence Detection in Dialog Systems](https://mlsanity.com/paper/1807.11567/) (2018)

## Built on by (most cited first, 6 of 6)

- [A Survey on Out-of-Distribution Detection in NLP](https://mlsanity.com/paper/2305.03236/) (2023)
- [Estimating Soft Labels for Out-of-Domain Intent Detection](https://mlsanity.com/paper/2211.05561/) (2022)
- [UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning](https://mlsanity.com/paper/2210.10722/) (2022)
- [SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank](https://mlsanity.com/paper/2305.14696/) (2023)
- [Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)](https://mlsanity.com/paper/2205.11887/) (2022)
- [One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning](https://mlsanity.com/paper/2407.09011/) (2024)

## 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.