{"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/one-representation-per-word-does-it-make","title":"One Representation per Word - Does it make Sense for Composition?","arxiv_id":"1702.06696","date":"2017-02-22","proceeding":"WS 2017 4","authors":["Thomas Kober","Julie Weeds","John Wilkie","Jeremy Reffin","David Weir"],"abstract":"In this paper, we investigate whether an a priori disambiguation of word\nsenses is strictly necessary or whether the meaning of a word in context can be\ndisambiguated through composition alone. We evaluate the performance of\noff-the-shelf single-vector and multi-sense vector models on a benchmark phrase\nsimilarity task and a novel task for word-sense discrimination. We find that\nsingle-sense vector models perform as well or better than multi-sense vector\nmodels despite arguably less clean elementary representations. Our findings\nfurthermore show that simple composition functions such as pointwise addition\nare able to recover sense specific information from a single-sense vector model\nremarkably well.","url_abs":"http://arxiv.org/abs/1702.06696v1","url_pdf":"http://arxiv.org/pdf/1702.06696v1.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":"one-representation-per-word-does-it-make","repo_url":"https://github.com/tttthomasssss/sense2017","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"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}