{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T20:06:37Z","timestamp":1781294797522,"version":"3.54.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3046253","type":"journal-article","created":{"date-parts":[[2020,12,21]],"date-time":"2020-12-21T22:20:36Z","timestamp":1608589236000},"page":"227710-227718","source":"Crossref","is-referenced-by-count":36,"title":["A Residual BiLSTM Model for Named Entity Recognition"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1721-6986","authenticated-orcid":false,"given":"Gang","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7924-2840","authenticated-orcid":false,"given":"Hongzhe","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref38","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref33","first-page":"142","article-title":"Introduction to the conll-2003 shared task: language-independent named entity recognition","author":"sang","year":"2003","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref32","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref31","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref30","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2023"},{"key":"ref36","author":"weischedel","year":"2013","journal-title":"OntoNotes Release 5 0"},{"key":"ref35","author":"weischedel","year":"2011","journal-title":"OntoNotes Release 2 0"},{"key":"ref34","first-page":"108","article-title":"The third international Chinese language processing bakeoff: Word segmentation and named entity recognition","author":"levow","year":"2006","journal-title":"Proc 5th Workshop Chin Lang Process"},{"key":"ref28","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1284"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1203"},{"key":"ref20","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc HLT-NAACL ACL"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00104"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1101"},{"key":"ref24","first-page":"2379","article-title":"An encoding strategy based word-character lstm for chinese ner","author":"liu","year":"2019","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1144"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/687"},{"key":"ref25","first-page":"3384","article-title":"Can-ner: Convolutional attention network for Chinese named entity recognition","author":"zhu","year":"2019","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1030"},{"key":"ref51","first-page":"751","article-title":"Graphie: A graph-based framework for information extraction","author":"qian","year":"2019","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref57","first-page":"1","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"clevert","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016236"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1217"},{"key":"ref54","first-page":"1896","article-title":"Robust lexical features for improved neural network named-entity recognition","author":"ghaddar","year":"2018","journal-title":"Proc 28th Int Conf Comput Linguistics"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1282"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1283"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-049-6_101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1064"},{"key":"ref40","article-title":"To tune or not to tune? How about the best of both worlds?","author":"wang","year":"2019","journal-title":"arXiv 1907 05338"},{"key":"ref12","first-page":"182","article-title":"Adversarial transfer learning for Chinese named entity recognition with selfattention mechanism","author":"cao","year":"2018","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref13","first-page":"566","article-title":"Named entity recognition with stack residual LSTM and trainable bias decoding","author":"tran","year":"2017","journal-title":"Proc 8th Int Joint Conf Natural Lang Process"},{"key":"ref14","first-page":"2923","article-title":"Neural paraphrase generation with stacked residual LSTM networks","author":"prakash","year":"2016","journal-title":"Proc 26th Int Conf Comput Linguistics"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-477"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref18","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref4","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"arXiv 1409 3215 [cs]"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref6","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"huang","year":"2015","journal-title":"arXiv 1508 01991"},{"key":"ref5","first-page":"207","article-title":"Attention-based bidirectional long short-term memory networks for relation classification","author":"zhou","year":"2017","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50496-4_20"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1279"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2025"},{"key":"ref46","article-title":"TENER: Adapting transformer encoder for named entity recognition","author":"yan","year":"2019","journal-title":"arXiv 1911 04474"},{"key":"ref45","first-page":"184","article-title":"Deep contextualized word representations","author":"yang","year":"2018","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref48","first-page":"713","article-title":"A unified model for cross-domain and semi-supervised named entity recognition in chinese social media","author":"he","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2113"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"ref41","article-title":"Pre-training with whole word masking for chinese BERT","author":"cui","year":"2019","journal-title":"arXiv 1906 08101"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1233"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1078"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09301306.pdf?arnumber=9301306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:41Z","timestamp":1639770941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9301306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3046253","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}