{"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/advances-in-pre-training-distributed-word","title":"Advances in Pre-Training Distributed Word Representations","arxiv_id":"1712.09405","date":"2017-12-26","proceeding":"LREC 2018 5","authors":["Tomas Mikolov","Edouard Grave","Piotr Bojanowski","Christian Puhrsch","Armand Joulin"],"abstract":"Many Natural Language Processing applications nowadays rely on pre-trained\nword representations estimated from large text corpora such as news\ncollections, Wikipedia and Web Crawl. In this paper, we show how to train\nhigh-quality word vector representations by using a combination of known tricks\nthat are however rarely used together. The main result of our work is the new\nset of publicly available pre-trained models that outperform the current state\nof the art by a large margin on a number of tasks.","url_abs":"http://arxiv.org/abs/1712.09405v1","url_pdf":"http://arxiv.org/pdf/1712.09405v1.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":"advances-in-pre-training-distributed-word","repo_url":"https://github.com/L-sky/concept-finder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"advances-in-pre-training-distributed-word","repo_url":"https://github.com/PrashantRanjan09/WordEmbeddings-Elmo-Fasttext-Word2Vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"advances-in-pre-training-distributed-word","repo_url":"https://github.com/RaRe-Technologies/gensim-data","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"advances-in-pre-training-distributed-word","repo_url":"https://github.com/Remiphilius/PoemesProfonds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"advances-in-pre-training-distributed-word","repo_url":"https://github.com/nageshsinghc4/deepwrap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.09405","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}