{"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/unified-named-entity-recognition-as-word-word","title":"Unified Named Entity Recognition as Word-Word Relation Classification","arxiv_id":"2112.10070","date":"2021-12-19","proceeding":null,"authors":["Jingye Li","Hao Fei","Jiang Liu","Shengqiong Wu","Meishan Zhang","Chong Teng","Donghong Ji","Fei Li"],"abstract":"So far, named entity recognition (NER) has been involved with three major types, including flat, overlapped (aka. nested), and discontinuous NER, which have mostly been studied individually. Recently, a growing interest has been built for unified NER, tackling the above three jobs concurrently with one single model. Current best-performing methods mainly include span-based and sequence-to-sequence models, where unfortunately the former merely focus on boundary identification and the latter may suffer from exposure bias. In this work, we present a novel alternative by modeling the unified NER as word-word relation classification, namely W^2NER. The architecture resolves the kernel bottleneck of unified NER by effectively modeling the neighboring relations between entity words with Next-Neighboring-Word (NNW) and Tail-Head-Word-* (THW-*) relations. Based on the W^2NER scheme we develop a neural framework, in which the unified NER is modeled as a 2D grid of word pairs. We then propose multi-granularity 2D convolutions for better refining the grid representations. Finally, a co-predictor is used to sufficiently reason the word-word relations. We perform extensive experiments on 14 widely-used benchmark datasets for flat, overlapped, and discontinuous NER (8 English and 6 Chinese datasets), where our model beats all the current top-performing baselines, pushing the state-of-the-art performances of unified NER.","url_abs":"https://arxiv.org/abs/2112.10070v1","url_pdf":"https://arxiv.org/pdf/2112.10070v1.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":"unified-named-entity-recognition-as-word-word","repo_url":"https://github.com/ljynlp/w2ner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"chinese-named-entity-recognition","task_name":"Chinese Named Entity Recognition"},{"task_slug":"classification-1","task_name":"Classification"},{"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":"nested-named-entity-recognition","task_name":"Nested Named Entity Recognition"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/chinese-named-entity-recognition-on-msra","task":"Chinese Named Entity Recognition","dataset":"MSRA","model":"W2NER","rank_in_archive_order":4,"of":21,"metrics":{"F1":"96.10"},"uses_additional_data":false},{"leaderboard":"/sota/chinese-named-entity-recognition-on-ontonotes","task":"Chinese Named Entity Recognition","dataset":"OntoNotes 4","model":"W2NER","rank_in_archive_order":2,"of":15,"metrics":{"F1":"83.08"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-conll-2003","task":"Named Entity Recognition (NER)","dataset":"CoNLL 2003 (English)","model":"W2NER","rank_in_archive_order":32,"of":73,"metrics":{"F1":"93.07"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-ontonotes-v5","task":"Named Entity Recognition (NER)","dataset":"Ontonotes v5 (English)","model":"W2NER","rank_in_archive_order":10,"of":28,"metrics":{"F1":"90.50"},"uses_additional_data":false},{"leaderboard":"/sota/nested-named-entity-recognition-on-ace-2004","task":"Nested Named Entity Recognition","dataset":"ACE 2004","model":"W2NER","rank_in_archive_order":10,"of":24,"metrics":{"F1":"87.52"},"uses_additional_data":false},{"leaderboard":"/sota/nested-named-entity-recognition-on-ace-2005","task":"Nested Named Entity Recognition","dataset":"ACE 2005","model":"W2NER","rank_in_archive_order":8,"of":25,"metrics":{"F1":"86.79"},"uses_additional_data":false},{"leaderboard":"/sota/nested-named-entity-recognition-on-genia","task":"Nested Named Entity Recognition","dataset":"GENIA","model":"W2NER","rank_in_archive_order":4,"of":26,"metrics":{"F1":"81.39"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2112.10070","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}