{"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/measuring-thematic-fit-with-distributional","title":"Measuring Thematic Fit with Distributional Feature Overlap","arxiv_id":"1707.05967","date":"2017-07-19","proceeding":"EMNLP 2017 9","authors":["Enrico Santus","Emmanuele Chersoni","Alessandro Lenci","Philippe Blache"],"abstract":"In this paper, we introduce a new distributional method for modeling\npredicate-argument thematic fit judgments. We use a syntax-based DSM to build a\nprototypical representation of verb-specific roles: for every verb, we extract\nthe most salient second order contexts for each of its roles (i.e. the most\nsalient dimensions of typical role fillers), and then we compute thematic fit\nas a weighted overlap between the top features of candidate fillers and role\nprototypes. Our experiments show that our method consistently outperforms a\nbaseline re-implementing a state-of-the-art system, and achieves better or\ncomparable results to those reported in the literature for the other\nunsupervised systems. Moreover, it provides an explicit representation of the\nfeatures characterizing verb-specific semantic roles.","url_abs":"http://arxiv.org/abs/1707.05967v2","url_pdf":"http://arxiv.org/pdf/1707.05967v2.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":"measuring-thematic-fit-with-distributional","repo_url":"https://github.com/esantus/Thematic_Fit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}