{"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/enhanced-meta-learning-for-cross-lingual","title":"Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources","arxiv_id":"1911.06161","date":"2019-11-14","proceeding":null,"authors":["Qianhui Wu","Zijia Lin","Guoxin Wang","Hui Chen","Börje F. Karlsson","Biqing Huang","Chin-Yew Lin"],"abstract":"For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target language, in this paper, we propose to fine-tune the learned model with a few similar examples given a test case, which could benefit the prediction by leveraging the structural and semantic information conveyed in such similar examples. To this end, we present a meta-learning algorithm to find a good model parameter initialization that could fast adapt to the given test case and propose to construct multiple pseudo-NER tasks for meta-training by computing sentence similarities. To further improve the model's generalization ability across different languages, we introduce a masking scheme and augment the loss function with an additional maximum term during meta-training. We conduct extensive experiments on cross-lingual named entity recognition with minimal resources over five target languages. The results show that our approach significantly outperforms existing state-of-the-art methods across the board.","url_abs":"https://arxiv.org/abs/1911.06161v2","url_pdf":"https://arxiv.org/pdf/1911.06161v2.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":"enhanced-meta-learning-for-cross-lingual","repo_url":"https://github.com/microsoft/vert-papers/tree/master/papers/Meta-Cross","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-lingual-ner","task_name":"Cross-Lingual NER"},{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"meta-learning","task_name":"Meta-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":"sentence","task_name":"Sentence"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-lingual-ner-on-conll-dutch","task":"Cross-Lingual NER","dataset":"CoNLL Dutch","model":"Meta-Cross","rank_in_archive_order":6,"of":10,"metrics":{"F1":"80.44"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-conll-dutch","task":"Cross-Lingual NER","dataset":"CoNLL Dutch","model":"Base Model","rank_in_archive_order":8,"of":10,"metrics":{"F1":"79.57"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-conll-german","task":"Cross-Lingual NER","dataset":"CoNLL German","model":"Meta-Cross","rank_in_archive_order":6,"of":10,"metrics":{"F1":"73.16"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-conll-german","task":"Cross-Lingual NER","dataset":"CoNLL German","model":"Base Model","rank_in_archive_order":8,"of":10,"metrics":{"F1":"70.79"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-conll-spanish","task":"Cross-Lingual NER","dataset":"CoNLL Spanish","model":"Meta-Cross","rank_in_archive_order":6,"of":10,"metrics":{"F1":"76.75"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-conll-spanish","task":"Cross-Lingual NER","dataset":"CoNLL Spanish","model":"Base Model","rank_in_archive_order":9,"of":10,"metrics":{"F1":"74.59"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-europeana-french","task":"Cross-Lingual NER","dataset":"Europeana French","model":"Meta-Cross","rank_in_archive_order":1,"of":2,"metrics":{"F1":"55.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-europeana-french","task":"Cross-Lingual NER","dataset":"Europeana French","model":"Base Model","rank_in_archive_order":2,"of":2,"metrics":{"F1":"50.89"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-msra","task":"Cross-Lingual NER","dataset":"MSRA","model":"Meta-Cross","rank_in_archive_order":1,"of":2,"metrics":{"F1":"77.89"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-msra","task":"Cross-Lingual NER","dataset":"MSRA","model":"Base Model","rank_in_archive_order":2,"of":2,"metrics":{"F1":"76.42"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.06161","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}