{"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/sketching-word-vectors-through-hashing","title":"Sketching Word Vectors Through Hashing","arxiv_id":"1705.04253","date":"2017-05-11","proceeding":null,"authors":["Behrang QasemiZadeh","Laura Kallmeyer"],"abstract":"We propose a new fast word embedding technique using hash functions. The\nmethod is a derandomization of a new type of random projections: By\ndisregarding the classic constraint used in designing random projections (i.e.,\npreserving pairwise distances in a particular normed space), our solution\nexploits extremely sparse non-negative random projections. Our experiments show\nthat the proposed method can achieve competitive results, comparable to neural\nembedding learning techniques, however, with only a fraction of the\ncomputational complexity of these methods. While the proposed derandomization\nenhances the computational and space complexity of our method, the possibility\nof applying weighting methods such as positive pointwise mutual information\n(PPMI) to our models after their construction (and at a reduced dimensionality)\nimparts a high discriminatory power to the resulting embeddings. Obviously,\nthis method comes with other known benefits of random projection-based\ntechniques such as ease of update.","url_abs":"http://arxiv.org/abs/1705.04253v2","url_pdf":"http://arxiv.org/pdf/1705.04253v2.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":"sketching-word-vectors-through-hashing","repo_url":"https://github.com/languagerecipes/LPCFG_Unsupervised_Frame_Induction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}