{"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/outflip-generating-out-of-domain-samples-for","title":"OutFlip: Generating Out-of-Domain Samples for Unknown Intent Detection with Natural Language Attack","arxiv_id":"2105.05601","date":"2021-05-12","proceeding":null,"authors":["DongHyun Choi","Myeong Cheol Shin","EungGyun Kim","Dong Ryeol Shin"],"abstract":"Out-of-domain (OOD) input detection is vital in a task-oriented dialogue system since the acceptance of unsupported inputs could lead to an incorrect response of the system. This paper proposes OutFlip, a method to generate out-of-domain samples using only in-domain training dataset automatically. A white-box natural language attack method HotFlip is revised to generate out-of-domain samples instead of adversarial examples. Our evaluation results showed that integrating OutFlip-generated out-of-domain samples into the training dataset could significantly improve an intent classification model's out-of-domain detection performance.","url_abs":"https://arxiv.org/abs/2105.05601v1","url_pdf":"https://arxiv.org/pdf/2105.05601v1.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":"outflip-generating-out-of-domain-samples-for","repo_url":"https://github.com/kakaoenterprise/OutFlip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"intent-classification","task_name":"Intent Classification"},{"task_slug":"intent-detection","task_name":"Intent Detection"},{"task_slug":"intent-classification-1","task_name":"intent-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.05601","atlas_url":"https://app.syntology.ai/?focus=2105.05601","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}