{"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/deep-active-learning-for-named-entity","title":"Deep Active Learning for Named Entity Recognition","arxiv_id":"1707.05928","date":"2017-07-19","proceeding":"WS 2017 8","authors":["Yanyao Shen","Hyokun Yun","Zachary C. Lipton","Yakov Kronrod","Animashree Anandkumar"],"abstract":"Deep learning has yielded state-of-the-art performance on many natural\nlanguage processing tasks including named entity recognition (NER). However,\nthis typically requires large amounts of labeled data. In this work, we\ndemonstrate that the amount of labeled training data can be drastically reduced\nwhen deep learning is combined with active learning. While active learning is\nsample-efficient, it can be computationally expensive since it requires\niterative retraining. To speed this up, we introduce a lightweight architecture\nfor NER, viz., the CNN-CNN-LSTM model consisting of convolutional character and\nword encoders and a long short term memory (LSTM) tag decoder. The model\nachieves nearly state-of-the-art performance on standard datasets for the task\nwhile being computationally much more efficient than best performing models. We\ncarry out incremental active learning, during the training process, and are\nable to nearly match state-of-the-art performance with just 25\\% of the\noriginal training data.","url_abs":"http://arxiv.org/abs/1707.05928v3","url_pdf":"http://arxiv.org/pdf/1707.05928v3.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":"deep-active-learning-for-named-entity","repo_url":"https://github.com/nlp-uoregon/famie","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"deep-active-learning-for-named-entity","repo_url":"https://github.com/tonygsw/Joint-Extraction-of-Entities-and-Relations-Based-on-a-Novel-Tagging-Scheme","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"decoder","task_name":"Decoder"},{"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":"tag","task_name":"TAG"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.05928","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}