{"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/tweet2vec-character-based-distributed","title":"Tweet2Vec: Character-Based Distributed Representations for Social Media","arxiv_id":"1605.03481","date":"2016-05-11","proceeding":"ACL 2016 8","authors":["Bhuwan Dhingra","Zhong Zhou","Dylan Fitzpatrick","Michael Muehl","William W. Cohen"],"abstract":"Text from social media provides a set of challenges that can cause\ntraditional NLP approaches to fail. Informal language, spelling errors,\nabbreviations, and special characters are all commonplace in these posts,\nleading to a prohibitively large vocabulary size for word-level approaches. We\npropose a character composition model, tweet2vec, which finds vector-space\nrepresentations of whole tweets by learning complex, non-local dependencies in\ncharacter sequences. The proposed model outperforms a word-level baseline at\npredicting user-annotated hashtags associated with the posts, doing\nsignificantly better when the input contains many out-of-vocabulary words or\nunusual character sequences. Our tweet2vec encoder is publicly available.","url_abs":"http://arxiv.org/abs/1605.03481v2","url_pdf":"http://arxiv.org/pdf/1605.03481v2.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":"tweet2vec-character-based-distributed","repo_url":"https://github.com/bdhingra/tweet2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}