{"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/comprehensive-supersense-disambiguation-of","title":"Comprehensive Supersense Disambiguation of English Prepositions and Possessives","arxiv_id":"1805.04905","date":"2018-05-13","proceeding":"ACL 2018 7","authors":["Nathan Schneider","Jena D. Hwang","Vivek Srikumar","Jakob Prange","Austin Blodgett","Sarah R. Moeller","Aviram Stern","Adi Bitan","Omri Abend"],"abstract":"Semantic relations are often signaled with prepositional or possessive\nmarking--but extreme polysemy bedevils their analysis and automatic\ninterpretation. We introduce a new annotation scheme, corpus, and task for the\ndisambiguation of prepositions and possessives in English. Unlike previous\napproaches, our annotations are comprehensive with respect to types and tokens\nof these markers; use broadly applicable supersense classes rather than\nfine-grained dictionary definitions; unite prepositions and possessives under\nthe same class inventory; and distinguish between a marker's lexical\ncontribution and the role it marks in the context of a predicate or scene.\nStrong interannotator agreement rates, as well as encouraging disambiguation\nresults with established supervised methods, speak to the viability of the\nscheme and task.","url_abs":"http://arxiv.org/abs/1805.04905v1","url_pdf":"http://arxiv.org/pdf/1805.04905v1.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":"comprehensive-supersense-disambiguation-of","repo_url":"https://github.com/nert-gu/streusle","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-understanding-on-streusle","task":"Natural Language Understanding","dataset":"STREUSLE","model":"BiLSTM + MLP (gold syntax)","rank_in_archive_order":7,"of":11,"metrics":{"Full F1 (Preps)":"58.9","Function F1 (Preps)":"73.4","Role F1 (Preps)":"62.2"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-understanding-on-streusle","task":"Natural Language Understanding","dataset":"STREUSLE","model":"SVM (feature-rich, gold syntax)","rank_in_archive_order":8,"of":11,"metrics":{"Full F1 (Preps)":"59.5","Function F1 (Preps)":"71.0","Role F1 (Preps)":"62.2"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-understanding-on-streusle","task":"Natural Language Understanding","dataset":"STREUSLE","model":"SVM (feature-rich, auto syntax)","rank_in_archive_order":9,"of":11,"metrics":{"Full F1 (Preps)":"55.7","Function F1 (Preps)":"66.7","Role F1 (Preps)":"58.2"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-understanding-on-streusle","task":"Natural Language Understanding","dataset":"STREUSLE","model":"BiLSTM + MLP (auto syntax)","rank_in_archive_order":10,"of":11,"metrics":{"Full F1 (Preps)":"53.6","Function F1 (Preps)":"66.7","Role F1 (Preps)":"56.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.04905","atlas_url":"https://app.syntology.ai/?focus=1805.04905","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}