{"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/predicting-semantic-relations-using-global","title":"Predicting Semantic Relations using Global Graph Properties","arxiv_id":"1808.08644","date":"2018-08-27","proceeding":"EMNLP 2018 10","authors":["Yuval Pinter","Jacob Eisenstein"],"abstract":"Semantic graphs, such as WordNet, are resources which curate natural language\non two distinguishable layers. On the local level, individual relations between\nsynsets (semantic building blocks) such as hypernymy and meronymy enhance our\nunderstanding of the words used to express their meanings. Globally, analysis\nof graph-theoretic properties of the entire net sheds light on the structure of\nhuman language as a whole. In this paper, we combine global and local\nproperties of semantic graphs through the framework of Max-Margin Markov Graph\nModels (M3GM), a novel extension of Exponential Random Graph Model (ERGM) that\nscales to large multi-relational graphs. We demonstrate how such global\nmodeling improves performance on the local task of predicting semantic\nrelations between synsets, yielding new state-of-the-art results on the WN18RR\ndataset, a challenging version of WordNet link prediction in which \"easy\"\nreciprocal cases are removed. In addition, the M3GM model identifies\nmultirelational motifs that are characteristic of well-formed lexical semantic\nontologies.","url_abs":"http://arxiv.org/abs/1808.08644v1","url_pdf":"http://arxiv.org/pdf/1808.08644v1.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":"predicting-semantic-relations-using-global","repo_url":"https://github.com/yuvalpinter/m3gm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-wn18rr","task":"Link Prediction","dataset":"WN18RR","model":"M3GM","rank_in_archive_order":17,"of":75,"metrics":{"Hits@1":"0.4537","Hits@10":"0.5902","MRR":"0.4983"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}