# UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning

arXiv: https://arxiv.org/abs/2210.10722 · HTML: https://mlsanity.com/paper/2210.10722/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 19 Oct 2022.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [DOC: Deep Open Classification of Text Documents](https://mlsanity.com/paper/1709.08716/) (2017)
- [From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots](https://mlsanity.com/paper/1801.01957/) (2018)
- [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)
- [Deep Open Intent Classification with Adaptive Decision Boundary](https://mlsanity.com/paper/2012.10209/) (2020)
- [Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning](https://mlsanity.com/paper/2105.14289/) (2021)
- [Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates](https://mlsanity.com/paper/1807.00072/) (2018)
- [Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems](https://mlsanity.com/paper/1705.00746/) (2017)
- [Energy-based Unknown Intent Detection with Data Manipulation](https://mlsanity.com/paper/2107.12542/) (2021)

## Built on by (most cited first, 5 of 5)

- [A Survey on Out-of-Distribution Detection in NLP](https://mlsanity.com/paper/2305.03236/) (2023)
- [Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection](https://mlsanity.com/paper/2402.17256/) (2024)
- [ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection](https://mlsanity.com/paper/2308.13517/) (2023)
- [Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition](https://mlsanity.com/paper/2310.10184/) (2023)
- [APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection](https://mlsanity.com/paper/2310.13380/) (2023)

## Abstract (arXiv)

Detecting out-of-domain (OOD) intents from user queries is essential for avoiding wrong operations in task-oriented dialogue systems. The key challenge is how to distinguish in-domain (IND) and OOD intents. Previous methods ignore the alignment between representation learning and scoring function, limiting the OOD detection performance. In this paper, we propose a unified neighborhood learning framework (UniNL) to detect OOD intents. Specifically, we design a K-nearest neighbor contrastive learning (KNCL) objective for representation learning and introduce a KNN-based scoring function for OOD detection. We aim to align representation learning with scoring function. Experiments and analysis on two benchmark datasets show the effectiveness of our method.