{"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/polyglot-contextual-representations-improve","title":"Polyglot Contextual Representations Improve Crosslingual Transfer","arxiv_id":"1902.09697","date":"2019-02-26","proceeding":"NAACL 2019 6","authors":["Phoebe Mulcaire","Jungo Kasai","Noah A. Smith"],"abstract":"We introduce Rosita, a method to produce multilingual contextual word\nrepresentations by training a single language model on text from multiple\nlanguages. Our method combines the advantages of contextual word\nrepresentations with those of multilingual representation learning. We produce\nlanguage models from dissimilar language pairs (English/Arabic and\nEnglish/Chinese) and use them in dependency parsing, semantic role labeling,\nand named entity recognition, with comparisons to monolingual and\nnon-contextual variants. Our results provide further evidence for the benefits\nof polyglot learning, in which representations are shared across multiple\nlanguages.","url_abs":"http://arxiv.org/abs/1902.09697v2","url_pdf":"http://arxiv.org/pdf/1902.09697v2.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":"polyglot-contextual-representations-improve","repo_url":"https://github.com/pmulcaire/rosita","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-role-labeling","task_name":"Semantic Role Labeling"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.09697","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}