{"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/document-similarity-for-texts-of-varying-1","title":"Document Similarity for Texts of Varying Lengths via Hidden Topics","arxiv_id":"1903.10675","date":"2019-03-26","proceeding":"ACL 2018 7","authors":["Hongyu Gong","Tarek Sakakini","Suma Bhat","JinJun Xiong"],"abstract":"Measuring similarity between texts is an important task for several\napplications. Available approaches to measure document similarity are\ninadequate for document pairs that have non-comparable lengths, such as a long\ndocument and its summary. This is because of the lexical, contextual and the\nabstraction gaps between a long document of rich details and its concise\nsummary of abstract information. In this paper, we present a document matching\napproach to bridge this gap, by comparing the texts in a common space of hidden\ntopics. We evaluate the matching algorithm on two matching tasks and find that\nit consistently and widely outperforms strong baselines. We also highlight the\nbenefits of incorporating domain knowledge to text matching.","url_abs":"http://arxiv.org/abs/1903.10675v1","url_pdf":"http://arxiv.org/pdf/1903.10675v1.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":"document-similarity-for-texts-of-varying-1","repo_url":"https://github.com/HongyuGong/Document-Similarity-via-Hidden-Topics","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"text-matching","task_name":"Text Matching"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.10675","atlas_url":"https://app.syntology.ai/?focus=1903.10675","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}