{"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/adversarial-domain-adaptation-for-duplicate","title":"Adversarial Domain Adaptation for Duplicate Question Detection","arxiv_id":"1809.02255","date":"2018-09-07","proceeding":"EMNLP 2018 10","authors":["Darsh J Shah","Tao Lei","Alessandro Moschitti","Salvatore Romeo","Preslav Nakov"],"abstract":"We address the problem of detecting duplicate questions in forums, which is\nan important step towards automating the process of answering new questions. As\nfinding and annotating such potential duplicates manually is very tedious and\ncostly, automatic methods based on machine learning are a viable alternative.\nHowever, many forums do not have annotated data, i.e., questions labeled by\nexperts as duplicates, and thus a promising solution is to use domain\nadaptation from another forum that has such annotations. Here we focus on\nadversarial domain adaptation, deriving important findings about when it\nperforms well and what properties of the domains are important in this regard.\nOur experiments with StackExchange data show an average improvement of 5.6%\nover the best baseline across multiple pairs of domains.","url_abs":"http://arxiv.org/abs/1809.02255v1","url_pdf":"http://arxiv.org/pdf/1809.02255v1.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":"adversarial-domain-adaptation-for-duplicate","repo_url":"https://github.com/darsh10/qra_code","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"question-similarity","task_name":"Question Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.02255","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}