{"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/better-word-embeddings-by-disentangling","title":"Better Word Embeddings by Disentangling Contextual n-Gram Information","arxiv_id":"1904.05033","date":"2019-04-10","proceeding":"NAACL 2019 6","authors":["Prakhar Gupta","Matteo Pagliardini","Martin Jaggi"],"abstract":"Pre-trained word vectors are ubiquitous in Natural Language Processing\napplications. In this paper, we show how training word embeddings jointly with\nbigram and even trigram embeddings, results in improved unigram embeddings. We\nclaim that training word embeddings along with higher n-gram embeddings helps\nin the removal of the contextual information from the unigrams, resulting in\nbetter stand-alone word embeddings. We empirically show the validity of our\nhypothesis by outperforming other competing word representation models by a\nsignificant margin on a wide variety of tasks. We make our models publicly\navailable.","url_abs":"http://arxiv.org/abs/1904.05033v1","url_pdf":"http://arxiv.org/pdf/1904.05033v1.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":"better-word-embeddings-by-disentangling","repo_url":"https://github.com/epfml/sent2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.05033","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}