{"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/zero-resource-cross-domain-named-entity","title":"Zero-Resource Cross-Domain Named Entity Recognition","arxiv_id":"2002.05923","date":"2020-02-14","proceeding":"WS 2020 7","authors":["Zihan Liu","Genta Indra Winata","Pascale Fung"],"abstract":"Existing models for cross-domain named entity recognition (NER) rely on numerous unlabeled corpus or labeled NER training data in target domains. However, collecting data for low-resource target domains is not only expensive but also time-consuming. Hence, we propose a cross-domain NER model that does not use any external resources. We first introduce a Multi-Task Learning (MTL) by adding a new objective function to detect whether tokens are named entities or not. We then introduce a framework called Mixture of Entity Experts (MoEE) to improve the robustness for zero-resource domain adaptation. Finally, experimental results show that our model outperforms strong unsupervised cross-domain sequence labeling models, and the performance of our model is close to that of the state-of-the-art model which leverages extensive resources.","url_abs":"https://arxiv.org/abs/2002.05923v2","url_pdf":"https://arxiv.org/pdf/2002.05923v2.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":"zero-resource-cross-domain-named-entity","repo_url":"https://github.com/Siddharthss500/zero-resource","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","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":"multi-task-learning","task_name":"Multi-Task 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":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-domain-named-entity-recognition-on","task":"Cross-Domain Named Entity Recognition","dataset":"CoNLL04","model":"BiLSTM w/ MTL and MoEE","rank_in_archive_order":1,"of":1,"metrics":{"F1":"70.04"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.05923","atlas_url":"https://app.syntology.ai/?focus=2002.05923","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}