{"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/insights-into-analogy-completion-from-the","title":"Insights into Analogy Completion from the Biomedical Domain","arxiv_id":"1706.02241","date":"2017-06-07","proceeding":"WS 2017 8","authors":["Denis Newman-Griffis","Albert M. Lai","Eric Fosler-Lussier"],"abstract":"Analogy completion has been a popular task in recent years for evaluating the\nsemantic properties of word embeddings, but the standard methodology makes a\nnumber of assumptions about analogies that do not always hold, either in recent\nbenchmark datasets or when expanding into other domains. Through an analysis of\nanalogies in the biomedical domain, we identify three assumptions: that of a\nSingle Answer for any given analogy, that the pairs involved describe the Same\nRelationship, and that each pair is Informative with respect to the other. We\npropose modifying the standard methodology to relax these assumptions by\nallowing for multiple correct answers, reporting MAP and MRR in addition to\naccuracy, and using multiple example pairs. We further present BMASS, a novel\ndataset for evaluating linguistic regularities in biomedical embeddings, and\ndemonstrate that the relationships described in the dataset pose significant\nsemantic challenges to current word embedding methods.","url_abs":"http://arxiv.org/abs/1706.02241v1","url_pdf":"http://arxiv.org/pdf/1706.02241v1.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":"insights-into-analogy-completion-from-the","repo_url":"https://github.com/OSU-slatelab/BMASS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}