{"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/few-shot-classification-in-named-entity","title":"Few-shot classification in Named Entity Recognition Task","arxiv_id":"1812.06158","date":"2018-12-14","proceeding":null,"authors":["Alexander Fritzler","Varvara Logacheva","Maksim Kretov"],"abstract":"For many natural language processing (NLP) tasks the amount of annotated data\nis limited. This urges a need to apply semi-supervised learning techniques,\nsuch as transfer learning or meta-learning. In this work we tackle Named Entity\nRecognition (NER) task using Prototypical Network - a metric learning\ntechnique. It learns intermediate representations of words which cluster well\ninto named entity classes. This property of the model allows classifying words\nwith extremely limited number of training examples, and can potentially be used\nas a zero-shot learning method. By coupling this technique with transfer\nlearning we achieve well-performing classifiers trained on only 20 instances of\na target class.","url_abs":"http://arxiv.org/abs/1812.06158v1","url_pdf":"http://arxiv.org/pdf/1812.06158v1.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":"few-shot-classification-in-named-entity","repo_url":"https://github.com/Fritz449/ProtoNER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"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":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.06158","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}