{"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/morphosyntactic-tagging-with-a-meta-bilstm","title":"Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive Token Encodings","arxiv_id":"1805.08237","date":"2018-05-21","proceeding":"ACL 2018 7","authors":["Bernd Bohnet","Ryan Mcdonald","Goncalo Simoes","Daniel Andor","Emily Pitler","Joshua Maynez"],"abstract":"The rise of neural networks, and particularly recurrent neural networks, has\nproduced significant advances in part-of-speech tagging accuracy. One\ncharacteristic common among these models is the presence of rich initial word\nencodings. These encodings typically are composed of a recurrent\ncharacter-based representation with learned and pre-trained word embeddings.\nHowever, these encodings do not consider a context wider than a single word and\nit is only through subsequent recurrent layers that word or sub-word\ninformation interacts. In this paper, we investigate models that use recurrent\nneural networks with sentence-level context for initial character and\nword-based representations. In particular we show that optimal results are\nobtained by integrating these context sensitive representations through\nsynchronized training with a meta-model that learns to combine their states. We\npresent results on part-of-speech and morphological tagging with\nstate-of-the-art performance on a number of languages.","url_abs":"http://arxiv.org/abs/1805.08237v1","url_pdf":"http://arxiv.org/pdf/1805.08237v1.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":"morphosyntactic-tagging-with-a-meta-bilstm","repo_url":"https://github.com/google/meta_tagger","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"morphosyntactic-tagging-with-a-meta-bilstm","repo_url":"https://github.com/qGentry/MetaBiLSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"morphological-tagging","task_name":"Morphological Tagging"},{"task_slug":"part-of-speech-tagging","task_name":"Part-Of-Speech Tagging"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/part-of-speech-tagging-on-penn-treebank","task":"Part-Of-Speech Tagging","dataset":"Penn Treebank","model":"Meta BiLSTM","rank_in_archive_order":2,"of":20,"metrics":{"Accuracy":"97.96"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.08237","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}