{"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/semi-supervised-sequence-tagging-with","title":"Semi-supervised sequence tagging with bidirectional language models","arxiv_id":"1705.00108","date":"2017-04-29","proceeding":"ACL 2017 7","authors":["Matthew E. Peters","Waleed Ammar","Chandra Bhagavatula","Russell Power"],"abstract":"Pre-trained word embeddings learned from unlabeled text have become a\nstandard component of neural network architectures for NLP tasks. However, in\nmost cases, the recurrent network that operates on word-level representations\nto produce context sensitive representations is trained on relatively little\nlabeled data. In this paper, we demonstrate a general semi-supervised approach\nfor adding pre- trained context embeddings from bidirectional language models\nto NLP systems and apply it to sequence labeling tasks. We evaluate our model\non two standard datasets for named entity recognition (NER) and chunking, and\nin both cases achieve state of the art results, surpassing previous systems\nthat use other forms of transfer or joint learning with additional labeled data\nand task specific gazetteers.","url_abs":"http://arxiv.org/abs/1705.00108v1","url_pdf":"http://arxiv.org/pdf/1705.00108v1.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":"semi-supervised-sequence-tagging-with","repo_url":"https://github.com/gaohuan2015/NLPTool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"chunking","task_name":"Chunking"},{"task_slug":"cg","task_name":"NER"},{"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":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.00108","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}