{"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/hierarchical-character-word-models-for","title":"Hierarchical Character-Word Models for Language Identification","arxiv_id":"1608.03030","date":"2016-08-10","proceeding":"WS 2016 11","authors":["Aaron Jaech","George Mulcaire","Shobhit Hathi","Mari Ostendorf","Noah A. Smith"],"abstract":"Social media messages' brevity and unconventional spelling pose a challenge\nto language identification. We introduce a hierarchical model that learns\ncharacter and contextualized word-level representations for language\nidentification. Our method performs well against strong base- lines, and can\nalso reveal code-switching.","url_abs":"http://arxiv.org/abs/1608.03030v1","url_pdf":"http://arxiv.org/pdf/1608.03030v1.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":"hierarchical-character-word-models-for","repo_url":"https://github.com/ajaech/twitter_langid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"language-identification","task_name":"Language Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}