{"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/a-unified-mrc-framework-for-named-entity","title":"A Unified MRC Framework for Named Entity Recognition","arxiv_id":"1910.11476","date":"2019-10-25","proceeding":"ACL 2020 6","authors":["Xiaoya Li","Jingrong Feng","Yuxian Meng","Qinghong Han","Fei Wu","Jiwei Li"],"abstract":"The task of named entity recognition (NER) is normally divided into nested NER and flat NER depending on whether named entities are nested or not. Models are usually separately developed for the two tasks, since sequence labeling models, the most widely used backbone for flat NER, are only able to assign a single label to a particular token, which is unsuitable for nested NER where a token may be assigned several labels. In this paper, we propose a unified framework that is capable of handling both flat and nested NER tasks. Instead of treating the task of NER as a sequence labeling problem, we propose to formulate it as a machine reading comprehension (MRC) task. For example, extracting entities with the \\textsc{per} label is formalized as extracting answer spans to the question \"{\\it which person is mentioned in the text?}\". This formulation naturally tackles the entity overlapping issue in nested NER: the extraction of two overlapping entities for different categories requires answering two independent questions. Additionally, since the query encodes informative prior knowledge, this strategy facilitates the process of entity extraction, leading to better performances for not only nested NER, but flat NER. We conduct experiments on both {\\em nested} and {\\em flat} NER datasets. Experimental results demonstrate the effectiveness of the proposed formulation. We are able to achieve vast amount of performance boost over current SOTA models on nested NER datasets, i.e., +1.28, +2.55, +5.44, +6.37, respectively on ACE04, ACE05, GENIA and KBP17, along with SOTA results on flat NER datasets, i.e.,+0.24, +1.95, +0.21, +1.49 respectively on English CoNLL 2003, English OntoNotes 5.0, Chinese MSRA, Chinese OntoNotes 4.0.","url_abs":"https://arxiv.org/abs/1910.11476v7","url_pdf":"https://arxiv.org/pdf/1910.11476v7.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":"a-unified-mrc-framework-for-named-entity","repo_url":"https://github.com/ShannonAI/mrc-for-flat-nested-ner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-unified-mrc-framework-for-named-entity","repo_url":"https://github.com/RohanSaxena14/mrc-for-flat-nested-ner-in-tensoflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-unified-mrc-framework-for-named-entity","repo_url":"https://github.com/ShannonAI/dice_loss_for_NLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-unified-mrc-framework-for-named-entity","repo_url":"https://github.com/allenyummy/EHR_NER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-unified-mrc-framework-for-named-entity","repo_url":"https://github.com/fulstock/mrc_nested_ner_ru","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-unified-mrc-framework-for-named-entity","repo_url":"https://github.com/manliu1225/mrc-for-flat-nested-ner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-unified-mrc-framework-for-named-entity","repo_url":"https://github.com/shuhewang1998/gpt-ner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-unified-mrc-framework-for-named-entity","repo_url":"https://github.com/thanhlt998/mrc-ner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"chinese-named-entity-recognition","task_name":"Chinese Named Entity Recognition"},{"task_slug":"entity-extraction","task_name":"Entity Extraction using GAN"},{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"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-mention-recognition","task_name":"Nested Mention Recognition"},{"task_slug":"nested-named-entity-recognition","task_name":"Nested Named Entity Recognition"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/chinese-named-entity-recognition-on-msra","task":"Chinese Named Entity Recognition","dataset":"MSRA","model":"BERT-MRC","rank_in_archive_order":6,"of":21,"metrics":{"F1":"95.75"},"uses_additional_data":true},{"leaderboard":"/sota/chinese-named-entity-recognition-on-ontonotes","task":"Chinese Named Entity Recognition","dataset":"OntoNotes 4","model":"BERT-MRC","rank_in_archive_order":4,"of":15,"metrics":{"F1":"82.11"},"uses_additional_data":true},{"leaderboard":"/sota/named-entity-recognition-on-ace-2005","task":"Named Entity Recognition (NER)","dataset":"ACE 2005","model":"BERT-MRC","rank_in_archive_order":7,"of":20,"metrics":{"F1":"86.88"},"uses_additional_data":true},{"leaderboard":"/sota/named-entity-recognition-ner-on-conll-2003","task":"Named Entity Recognition (NER)","dataset":"CoNLL 2003 (English)","model":"BERT-MRC","rank_in_archive_order":33,"of":73,"metrics":{"F1":"93.04"},"uses_additional_data":true},{"leaderboard":"/sota/named-entity-recognition-ner-on-ontonotes-v5","task":"Named Entity Recognition (NER)","dataset":"Ontonotes v5 (English)","model":"BERT-MRC","rank_in_archive_order":5,"of":28,"metrics":{"F1":"91.11"},"uses_additional_data":true},{"leaderboard":"/sota/nested-mention-recognition-on-ace-2004","task":"Nested Mention Recognition","dataset":"ACE 2004","model":"BERT-MRC","rank_in_archive_order":2,"of":7,"metrics":{"F1":"85.98"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.11476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.11476"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allenyummy/EHR_NER","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShannonAI/dice_loss_for_NLP","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thanhlt998/mrc-ner","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/manliu1225/mrc-for-flat-nested-ner","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShannonAI/mrc-for-flat-nested-ner","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fulstock/mrc_nested_ner_ru","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RohanSaxena14/mrc-for-flat-nested-ner-in-tensoflow","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shuhewang1998/gpt-ner","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"2d3bc706749ed910","entry":"find_best_checkpoint_on_dev","repo":"ShannonAI/mrc-for-flat-nested-ner","repo_kind":"official","path":"train/mrc_ner_trainer.py","file_url":"https://github.com/ShannonAI/mrc-for-flat-nested-ner/blob/HEAD/train/mrc_ner_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d3bc706749ed910"}},{"code_sha256_prefix":"5da463d88de4e445","entry":"get_query_index_to_label_cate","repo":"ShannonAI/mrc-for-flat-nested-ner","repo_kind":"official","path":"inference/mrc_ner_inference.py","file_url":"https://github.com/ShannonAI/mrc-for-flat-nested-ner/blob/HEAD/inference/mrc_ner_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5da463d88de4e445"}},{"code_sha256_prefix":"417c959e616c6a6c","entry":"accuracy","repo":"RohanSaxena14/mrc-for-flat-nested-ner-in-tensoflow","repo_kind":"listed","path":"trainer.py","file_url":"https://github.com/RohanSaxena14/mrc-for-flat-nested-ner-in-tensoflow/blob/HEAD/trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"417c959e616c6a6c"}},{"code_sha256_prefix":"adc2b70193ffdf11","entry":"recall","repo":"RohanSaxena14/mrc-for-flat-nested-ner-in-tensoflow","repo_kind":"listed","path":"trainer.py","file_url":"https://github.com/RohanSaxena14/mrc-for-flat-nested-ner-in-tensoflow/blob/HEAD/trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"adc2b70193ffdf11"}},{"code_sha256_prefix":"2773fe08183391ad","entry":"span_matrix_func","repo":"RohanSaxena14/mrc-for-flat-nested-ner-in-tensoflow","repo_kind":"listed","path":"trainer.py","file_url":"https://github.com/RohanSaxena14/mrc-for-flat-nested-ner-in-tensoflow/blob/HEAD/trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2773fe08183391ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}