{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/uninl-aligning-representation-learning-with","title":"UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning","arxiv_id":"2210.10722","date":"2022-10-19","proceeding":null,"authors":["Yutao Mou","Pei Wang","Keqing He","Yanan Wu","Jingang Wang","Wei Wu","Weiran Xu"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2210.10722v1","url_pdf":"https://arxiv.org/pdf/2210.10722v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"uninl-aligning-representation-learning-with","repo_url":"https://github.com/yupei-wang/uninl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"ood-detection","task_name":"Out of Distribution (OOD) Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"task-oriented-dialogue-systems","task_name":"Task-Oriented Dialogue Systems"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.10722","atlas_url":"https://app.syntology.ai/?focus=2210.10722","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}