{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T19:18:30Z","timestamp":1785352710640,"version":"3.55.0"},"reference-count":49,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T00:00:00Z","timestamp":1697760000000},"content-version":"vor","delay-in-days":292,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Named Entity Recognition (NER) has so far evolved from the traditional flat NER to overlapped and discontinuous NER. They have mostly been solved separately, with only several exceptions that concurrently tackle three tasks with a single model. The current best-performing method formalizes the unified NER as word-word relation classification, which barely focuses on mention content learning and fails to detect entity mentions comprising a single word. In this paper, we propose a two-stage span-based framework with templates, namely, T2-NER, to resolve the unified NER task. The first stage is to extract entity spans, where flat and overlapped entities can be recognized. The second stage is to classify over all entity span pairs, where discontinuous entities can be recognized. Finally, multi-task learning is used to jointly train two stages. To improve the efficiency of span-based model, we design grouped templates and typed templates for two stages to realize batch computations. We also apply an adjacent packing strategy and a latter packing strategy to model discriminative boundary information and learn better span (pair) representation. Moreover, we introduce the syntax information to enhance our span representation. We perform extensive experiments on eight benchmark datasets for flat, overlapped, and discontinuous NER, where our model beats all the current competitive baselines, obtaining the best performance of unified NER.<\/jats:p>","DOI":"10.1162\/tacl_a_00602","type":"journal-article","created":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T13:19:50Z","timestamp":1697807990000},"page":"1265-1282","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":21,"title":["<i>T<\/i>\n          2\n          <i>-NER<\/i>: A <u>T<\/u>wo-Stage Span-Based Framework for Unified Named Entity Recognition with <u>T<\/u>emplates"],"prefix":"10.1162","volume":"11","author":[{"given":"Peixin","family":"Huang","sequence":"first","affiliation":[{"name":"National University of Defense Technology, Changsha, China. huangpeixin15@nudt.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China. xiangzhao@nudt.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghao","family":"Hu","sequence":"additional","affiliation":[{"name":"Information Research Center of Military Science, Beijing, China. huminghao16@gmail.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Tan","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China. tanzhen08a@nudt.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Xiao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China. wdxiao@nudt.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2023,10,20]]},"reference":[{"key":"2023102013193427200_bib1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1909","article-title":"Publicly available clinical BERT embeddings","volume":"abs\/1904.03323v3","author":"Alsentzer","year":"2019","journal-title":"CoRR"},{"key":"2023102013193427200_bib2","doi-asserted-by":"publisher","first-page":"261","DOI":"10.18653\/v1\/D19-1025","article-title":"Low-resource name tagging learned with weakly labeled data","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Cao","year":"2019"},{"key":"2023102013193427200_bib3","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"2023102013193427200_bib4","doi-asserted-by":"publisher","first-page":"1835","DOI":"10.18653\/v1\/2021.findings-acl.161","article-title":"Template-based named entity recognition using BART","volume-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","author":"Cui","year":"2021"},{"key":"2023102013193427200_bib5","doi-asserted-by":"publisher","first-page":"5860","DOI":"10.18653\/v1\/2020.acl-main.520","article-title":"An effective transition-based model for discontinuous NER","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Dai","year":"2020"},{"key":"2023102013193427200_bib6","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/v1\/N19-1423","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019"},{"key":"2023102013193427200_bib7","article-title":"The automatic content extraction (ACE) program - Tasks, data, and evaluation","volume-title":"Proceedings of the Language Resources and Evaluation Conference, May. 2004","author":"Doddington","year":"2004"},{"key":"2023102013193427200_bib8","doi-asserted-by":"publisher","first-page":"12785","DOI":"10.1609\/aaai.v35i14.17513","article-title":"Rethinking boundaries: End-to-end recognition of discontinuous mentions with pointer networks","volume-title":"Proceedings of the AAAI Conference February. 2021","author":"Fei","year":"2021"},{"key":"2023102013193427200_bib9","doi-asserted-by":"publisher","first-page":"141","DOI":"10.3115\/1699510.1699529","article-title":"Nested named entity recognition","volume-title":"Proceedings of the EMNLP Conference August. 2009","author":"Finkel","year":"2009"},{"key":"2023102013193427200_bib10","doi-asserted-by":"publisher","first-page":"241","DOI":"10.18653\/v1\/P19-1024","article-title":"Attention guided graph convolutional networks for relation extraction","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Guo","year":"2019"},{"key":"2023102013193427200_bib11","doi-asserted-by":"publisher","first-page":"85","DOI":"10.18653\/v1\/2022.findings-acl.9","article-title":"Extract-select: A span selection framework for nested named entity recognition with generative adversarial training","volume-title":"Findings of the Association for Computational Linguistics: ACL 2022","author":"Huang","year":"2022"},{"key":"2023102013193427200_bib12","doi-asserted-by":"publisher","first-page":"1446","DOI":"10.18653\/v1\/N18-1131","article-title":"A neural layered model for nested named entity recognition","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Meizhi","year":"2018"},{"key":"2023102013193427200_bib13","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.jbi.2015.03.010","article-title":"CADEC: A corpus of adverse drug event annotations","volume":"55","author":"Karimi","year":"2015","journal-title":"Journal of Biomedical Informatics"},{"key":"2023102013193427200_bib14","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1093\/bioinformatics\/btg1023","article-title":"GENIA corpus\u2014A semantically annotated corpus for bio-textmining","volume-title":"Proceedings of the International Conference on Intelligent Systems for Molecular Biology, June 29\u2013July 3. 2003","author":"Kim","year":"2003"},{"key":"2023102013193427200_bib15","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proceedings of the 5th ICLR Conference April. 2017","author":"Kipf","year":"2017"},{"key":"2023102013193427200_bib16","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","volume-title":"Proceedings of the ICML Conference June 28 \u2013 July 1. 2001","author":"Lafferty","year":"2001"},{"key":"2023102013193427200_bib17","doi-asserted-by":"publisher","first-page":"1595","DOI":"10.18653\/v1\/P18-1148","article-title":"Improving entity linking by modeling latent relations between mentions","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Le","year":"2018"},{"issue":"4","key":"2023102013193427200_bib18","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: A pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"2023102013193427200_bib19","doi-asserted-by":"publisher","first-page":"188","DOI":"10.18653\/v1\/D17-1018","article-title":"End-to-end neural coreference resolution","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Lee","year":"2017"},{"key":"2023102013193427200_bib20","doi-asserted-by":"publisher","first-page":"7871","DOI":"10.18653\/v1\/2020.acl-main.703","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Lewis","year":"2020"},{"key":"2023102013193427200_bib21","doi-asserted-by":"publisher","first-page":"4814","DOI":"10.18653\/v1\/2021.acl-long.372","article-title":"A span-based model for joint overlapped and discontinuous named entity recognition","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Li","year":"2021"},{"key":"2023102013193427200_bib22","doi-asserted-by":"publisher","first-page":"10965","DOI":"10.1609\/aaai.v36i10.21344","article-title":"Unified named entity recognition as word-word relation classification","volume-title":"Proceedings of the AAAI Conference February 22 \u2013 March 1. 2022","author":"Li","year":"2022"},{"key":"2023102013193427200_bib23","doi-asserted-by":"publisher","first-page":"5849","DOI":"10.18653\/v1\/2020.acl-main.519","article-title":"A unified MRC framework for named entity recognition","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Li","year":"2020"},{"key":"2023102013193427200_bib24","doi-asserted-by":"publisher","first-page":"5182","DOI":"10.18653\/v1\/P19-1511","article-title":"Sequence-to-nuggets: Nested entity mention detection via anchor-region networks","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Lin","year":"2019"},{"key":"2023102013193427200_bib25","article-title":"Decoupled weight decay regularization","volume-title":"Proceedings of the ICLR Conference May. 2019","author":"Loshchilov","year":"2019"},{"key":"2023102013193427200_bib26","doi-asserted-by":"publisher","first-page":"857","DOI":"10.18653\/v1\/D15-1102","article-title":"Joint mention extraction and classification with mention hypergraphs","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Wei","year":"2015"},{"key":"2023102013193427200_bib27","doi-asserted-by":"publisher","first-page":"3036","DOI":"10.18653\/v1\/N19-1308","article-title":"A general framework for information extraction using dynamic span graphs","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Yi","year":"2019"},{"key":"2023102013193427200_bib28","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3115\/v1\/P14-5010","article-title":"The stanford coreNLP natural language processing toolkit","volume-title":"Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Manning","year":"2014"},{"key":"2023102013193427200_bib29","first-page":"31","article-title":"Task 2: ShARe\/CLEF eHealth evaluation lab 2014","volume-title":"Working Notes for CLEF Conference September. 2014","author":"Mowery","year":"2014"},{"key":"2023102013193427200_bib30","doi-asserted-by":"crossref","first-page":"75","DOI":"10.18653\/v1\/D16-1008","article-title":"Learning to recognize discontiguous entities","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Muis","year":"2016"},{"key":"2023102013193427200_bib31","article-title":"Task 1: ShARe\/CLEF eHealth evaluation lab 2013","volume-title":"Working Notes for CLEF Conference September. 2013","author":"Pradhan","year":"2013"},{"key":"2023102013193427200_bib32","first-page":"143","article-title":"Towards robust linguistic analysis using OntoNotes","volume-title":"Proceedings of the 17th Conference Computational Natural Language Learning, August. 2013","author":"Pradhan","year":"2013"},{"key":"2023102013193427200_bib33","doi-asserted-by":"publisher","first-page":"142","DOI":"10.3115\/1119176.1119195","article-title":"Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition","volume-title":"Proceedings of the 7th Conference Natural Language Learning, May 31 \u2013 June 1. 2003","author":"Tjong Kim Sang","year":"2003"},{"key":"2023102013193427200_bib34","doi-asserted-by":"publisher","first-page":"2782","DOI":"10.18653\/v1\/2021.acl-long.216","article-title":"Locate and label: A two-stage identifier for nested named entity recognition","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Shen","year":"2021"},{"key":"2023102013193427200_bib35","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1162\/tacl_a_00334","article-title":"Nested named entity recognition via second-best sequence learning and decoding","volume":"8","author":"Shibuya","year":"2020","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2023102013193427200_bib36","doi-asserted-by":"publisher","first-page":"2843","DOI":"10.18653\/v1\/D18-1309","article-title":"Deep exhaustive model for nested named entity recognition","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Sohrab","year":"2018"},{"key":"2023102013193427200_bib37","doi-asserted-by":"publisher","first-page":"5326","DOI":"10.18653\/v1\/P19-1527","article-title":"Neural architectures for nested NER through linearization","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Strakov\u00e1","year":"2019"},{"key":"2023102013193427200_bib38","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/2379208","article-title":"Recognizing continuous and discontinuous adverse drug reaction mentions from social media using LSTM-CRF","volume":"2018","author":"Tang","year":"2018","journal-title":"Wireless Communications and Mobile Computing"},{"key":"2023102013193427200_bib39","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems December. 2017","author":"Vaswani","year":"2017"},{"issue":"110","key":"2023102013193427200_bib40","first-page":"261","article-title":"ACE 2005 multilingual training corpus LDC2006T06","volume":"110","author":"Walker","year":"2006","journal-title":"Web Download. Philadelphia: Linguistic Data Consortium"},{"key":"2023102013193427200_bib41","doi-asserted-by":"publisher","first-page":"204","DOI":"10.18653\/v1\/D18-1019","article-title":"Neural segmental hypergraphs for overlapping mention recognition","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Wang","year":"2018"},{"key":"2023102013193427200_bib42","doi-asserted-by":"publisher","first-page":"6215","DOI":"10.18653\/v1\/D19-1644","article-title":"Combining spans into entities: A neural two-stage approach for recognizing discontiguous entities","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Wang","year":"2019"},{"key":"2023102013193427200_bib43","doi-asserted-by":"publisher","first-page":"1011","DOI":"10.18653\/v1\/D18-1124","article-title":"A neural transition-based model for nested mention recognition","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Wang","year":"2018"},{"key":"2023102013193427200_bib44","doi-asserted-by":"publisher","first-page":"764","DOI":"10.18653\/v1\/2021.acl-long.63","article-title":"Discontinuous named entity recognition as maximal clique discovery","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Wang","year":"2021"},{"key":"2023102013193427200_bib45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.04474","article-title":"TENER: Adapting transformer encoder for named entity recognition","volume":"abs\/1911.04474v3","author":"Yan","year":"2019","journal-title":"CoRR"},{"key":"2023102013193427200_bib46","doi-asserted-by":"publisher","first-page":"5808","DOI":"10.18653\/v1\/2021.acl-long.451","article-title":"A unified generative framework for various NER subtasks","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Yan","year":"2021"},{"key":"2023102013193427200_bib47","doi-asserted-by":"publisher","first-page":"6470","DOI":"10.18653\/v1\/2020.acl-main.577","article-title":"Named entity recognition as dependency parsing","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Juntao","year":"2020"},{"key":"2023102013193427200_bib48","doi-asserted-by":"publisher","first-page":"50","DOI":"10.18653\/v1\/2021.naacl-main.5","article-title":"A frustratingly easy approach for entity and relation extraction","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Zhong","year":"2021"},{"key":"2023102013193427200_bib49","first-page":"434","article-title":"Fast and accurate shift-reduce constituent parsing","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Zhu","year":"2013"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00602\/2163493\/tacl_a_00602.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00602\/2163493\/tacl_a_00602.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T13:20:00Z","timestamp":1697808000000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00602\/117872\/T2-NER-A-Two-Stage-Span-Based-Framework-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00602","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}