{"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/neural-adaptation-layers-for-cross-domain","title":"Neural Adaptation Layers for Cross-domain Named Entity Recognition","arxiv_id":"1810.06368","date":"2018-10-15","proceeding":"EMNLP 2018 10","authors":["Bill Yuchen Lin","Wei Lu"],"abstract":"Recent research efforts have shown that neural architectures can be effective\nin conventional information extraction tasks such as named entity recognition,\nyielding state-of-the-art results on standard newswire datasets. However,\ndespite significant resources required for training such models, the\nperformance of a model trained on one domain typically degrades dramatically\nwhen applied to a different domain, yet extracting entities from new emerging\ndomains such as social media can be of significant interest. In this paper, we\nempirically investigate effective methods for conveniently adapting an\nexisting, well-trained neural NER model for a new domain. Unlike existing\napproaches, we propose lightweight yet effective methods for performing domain\nadaptation for neural models. Specifically, we introduce adaptation layers on\ntop of existing neural architectures, where no re-training using the source\ndomain data is required. We conduct extensive empirical studies and show that\nour approach significantly outperforms state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1810.06368v1","url_pdf":"http://arxiv.org/pdf/1810.06368v1.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":"neural-adaptation-layers-for-cross-domain","repo_url":"https://github.com/yuchenlin/CDMA-NER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"cross-domain-named-entity-recognition","task_name":"Cross-Domain Named Entity Recognition"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"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":{"syntology_url":"https://syntology.ai/paper/1810.06368","atlas_url":"https://app.syntology.ai/?focus=1810.06368","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}