{"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/sparse-overcomplete-word-vector","title":"Sparse Overcomplete Word Vector Representations","arxiv_id":"1506.02004","date":"2015-06-05","proceeding":"IJCNLP 2015 7","authors":["Manaal Faruqui","Yulia Tsvetkov","Dani Yogatama","Chris Dyer","Noah Smith"],"abstract":"Current distributed representations of words show little resemblance to\ntheories of lexical semantics. The former are dense and uninterpretable, the\nlatter largely based on familiar, discrete classes (e.g., supersenses) and\nrelations (e.g., synonymy and hypernymy). We propose methods that transform\nword vectors into sparse (and optionally binary) vectors. The resulting\nrepresentations are more similar to the interpretable features typically used\nin NLP, though they are discovered automatically from raw corpora. Because the\nvectors are highly sparse, they are computationally easy to work with. Most\nimportantly, we find that they outperform the original vectors on benchmark\ntasks.","url_abs":"http://arxiv.org/abs/1506.02004v1","url_pdf":"http://arxiv.org/pdf/1506.02004v1.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":"sparse-overcomplete-word-vector","repo_url":"https://github.com/mfaruqui/sparse-coding","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sparse-overcomplete-word-vector","repo_url":"https://github.com/harsh19/SPINE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"sparse-overcomplete-word-vector","repo_url":"https://github.com/jacobdanovitch/spine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.02004","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}