{"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/matrix-factorization-using-window-sampling","title":"Matrix Factorization using Window Sampling and Negative Sampling for Improved Word Representations","arxiv_id":"1606.00819","date":"2016-06-02","proceeding":"ACL 2016 8","authors":["Alexandre Salle","Marco Idiart","Aline Villavicencio"],"abstract":"In this paper, we propose LexVec, a new method for generating distributed\nword representations that uses low-rank, weighted factorization of the Positive\nPoint-wise Mutual Information matrix via stochastic gradient descent, employing\na weighting scheme that assigns heavier penalties for errors on frequent\nco-occurrences while still accounting for negative co-occurrence. Evaluation on\nword similarity and analogy tasks shows that LexVec matches and often\noutperforms state-of-the-art methods on many of these tasks.","url_abs":"http://arxiv.org/abs/1606.00819v2","url_pdf":"http://arxiv.org/pdf/1606.00819v2.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":"matrix-factorization-using-window-sampling","repo_url":"https://github.com/alexandres/lexvec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"word-similarity","task_name":"Word Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.00819","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}