{"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/word2bits-quantized-word-vectors","title":"Word2Bits - Quantized Word Vectors","arxiv_id":"1803.05651","date":"2018-03-15","proceeding":null,"authors":["Maximilian Lam"],"abstract":"Word vectors require significant amounts of memory and storage, posing issues\nto resource limited devices like mobile phones and GPUs. We show that high\nquality quantized word vectors using 1-2 bits per parameter can be learned by\nintroducing a quantization function into Word2Vec. We furthermore show that\ntraining with the quantization function acts as a regularizer. We train word\nvectors on English Wikipedia (2017) and evaluate them on standard word\nsimilarity and analogy tasks and on question answering (SQuAD). Our quantized\nword vectors not only take 8-16x less space than full precision (32 bit) word\nvectors but also outperform them on word similarity tasks and question\nanswering.","url_abs":"http://arxiv.org/abs/1803.05651v3","url_pdf":"http://arxiv.org/pdf/1803.05651v3.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":"word2bits-quantized-word-vectors","repo_url":"https://github.com/agnusmaximus/Word2Bits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"word-similarity","task_name":"Word Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.05651","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}