{"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/universal-ner-a-gold-standard-multilingual-1","title":"Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark","arxiv_id":"2311.09122","date":"2023-11-15","proceeding":"arXiv 2023 11","authors":["Stephen Mayhew","Terra Blevins","Shuheng Liu","Marek Šuppa","Hila Gonen","Joseph Marvin Imperial","Börje F. Karlsson","Peiqin Lin","Nikola Ljubešić","LJ Miranda","Barbara Plank","Arij Riabi","Yuval Pinter"],"abstract":"We introduce Universal NER (UNER), an open, community-driven project to develop gold-standard NER benchmarks in many languages. The overarching goal of UNER is to provide high-quality, cross-lingually consistent annotations to facilitate and standardize multilingual NER research. UNER v1 contains 18 datasets annotated with named entities in a cross-lingual consistent schema across 12 diverse languages. In this paper, we detail the dataset creation and composition of UNER; we also provide initial modeling baselines on both in-language and cross-lingual learning settings. We release the data, code, and fitted models to the public.","url_abs":"https://arxiv.org/abs/2311.09122v3","url_pdf":"https://arxiv.org/pdf/2311.09122v3.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":"universal-ner-a-gold-standard-multilingual-1","repo_url":"https://github.com/opennlg/openba-v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"universal-ner-a-gold-standard-multilingual-1","repo_url":"https://github.com/UniversalNER/uner_code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"cross-lingual-ner","task_name":"Cross-Lingual NER"},{"task_slug":"multilingual-named-entity-recognition","task_name":"Multilingual Named Entity Recognition"},{"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":[{"slug":"uner-v1","name":"UNER v1","full_name":"Universal NER v1"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-cebuano","task":"Cross-Lingual NER","dataset":"UNER v1 (Cebuano)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"69.6"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-chinese-1","task":"Cross-Lingual NER","dataset":"UNER v1 (Chinese Simplified)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"87.7"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-chinese","task":"Cross-Lingual NER","dataset":"UNER v1 (Chinese)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"88.2"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-croatian","task":"Cross-Lingual NER","dataset":"UNER v1 (Croatian)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"90.9"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-danish","task":"Cross-Lingual NER","dataset":"UNER v1 (Danish)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"83.0"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-english","task":"Cross-Lingual NER","dataset":"UNER v1 (English)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"82.8"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-portuguese","task":"Cross-Lingual NER","dataset":"UNER v1 (Portuguese)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"82.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-serbian","task":"Cross-Lingual NER","dataset":"UNER v1 (Serbian)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"95.2"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-slovak","task":"Cross-Lingual NER","dataset":"UNER v1 (Slovak)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"81.6"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-swedish","task":"Cross-Lingual NER","dataset":"UNER v1 (Swedish)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"88.2"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-tagalog-t","task":"Cross-Lingual NER","dataset":"UNER v1 (Tagalog T)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"91.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-tagalog-u","task":"Cross-Lingual NER","dataset":"UNER v1 (Tagalog U)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"63.8"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-pud-chinese","task":"Cross-Lingual NER","dataset":"UNER v1 - PUD (Chinese)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"86.0"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-pud-english","task":"Cross-Lingual NER","dataset":"UNER v1 - PUD (English)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"79.5"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-pud-german","task":"Cross-Lingual NER","dataset":"UNER v1 - PUD (German)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"78.9"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-pud-portuguese","task":"Cross-Lingual NER","dataset":"UNER v1 - PUD (Portuguese)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"85.1"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-pud-russian","task":"Cross-Lingual NER","dataset":"UNER v1 - PUD (Russian)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"70.6"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-uner-v1-pud-swedish","task":"Cross-Lingual NER","dataset":"UNER v1 - PUD (Swedish)","model":"UNER XML-R (all)","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"85.3"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-8","task":"Named Entity Recognition (NER)","dataset":"UNER v1 (Chinese Simplified)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"89.40"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-7","task":"Named Entity Recognition (NER)","dataset":"UNER v1 (Chinese)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"89.50"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-2","task":"Named Entity Recognition (NER)","dataset":"UNER v1 (Croatian)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"93.60"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1","task":"Named Entity Recognition (NER)","dataset":"UNER v1 (Danish)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"82.70"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-1","task":"Named Entity Recognition (NER)","dataset":"UNER v1 (English)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"86.00"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-3","task":"Named Entity Recognition (NER)","dataset":"UNER v1 (Portuguese)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"90.4"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-5","task":"Named Entity Recognition (NER)","dataset":"UNER v1 (Serbian)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"94.70"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-4","task":"Named Entity Recognition (NER)","dataset":"UNER v1 (Slovak)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"85.50"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-6","task":"Named Entity Recognition (NER)","dataset":"UNER v1 (Swedish)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"88.30"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-pud-3","task":"Named Entity Recognition (NER)","dataset":"UNER v1 - PUD (Chinese)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"87.10"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-pud","task":"Named Entity Recognition (NER)","dataset":"UNER v1 - PUD (English)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"80.10"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-pud-1","task":"Named Entity Recognition (NER)","dataset":"UNER v1 - PUD (Portuguese)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"88.80"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-uner-v1-pud-2","task":"Named Entity Recognition (NER)","dataset":"UNER v1 - PUD (Swedish)","model":"UNER XML-R","rank_in_archive_order":1,"of":1,"metrics":{"F1 (micro)":"82.20"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.09122","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}