{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T07:38:35Z","timestamp":1781077115247,"version":"3.54.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976180"],"award-info":[{"award-number":["61976180"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3065201","type":"journal-article","created":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T21:16:16Z","timestamp":1615497376000},"page":"1318-1328","source":"Crossref","is-referenced-by-count":27,"title":["Improving Skip-Gram Embeddings Using BERT"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8705-9598","authenticated-orcid":false,"given":"Yile","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leyang","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5214-2268","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1198"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2501"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.07.005"},{"key":"ref39","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013"},{"key":"ref38","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv 1609 08144"},{"key":"ref33","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2050"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1142"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1006"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref35","article-title":"Longformer: The long-document transformer","author":"beltagy","year":"2020","journal-title":"arXiv 2004 05150"},{"key":"ref34","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"arXiv 1907 11692"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1101"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"ref63","first-page":"3879","article-title":"Design challenges and misconceptions in neural sequence labeling","author":"yang","year":"0","journal-title":"COLING"},{"key":"ref28","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1058"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1320"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref66","first-page":"47","article-title":"Introducing and evaluating ukwac, a very large web-derived corpus of English","author":"ferraresi","year":"0","journal-title":"Proc 4th Web Corpus Workshop (WAC-4) Can we beat Google"},{"key":"ref29","article-title":"Visualizing and measuring the geometry of BERT","volume":"32","author":"reif","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620758"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1175"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-1622"},{"key":"ref2","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1006"},{"key":"ref22","first-page":"196","article-title":"How self-attention improves rare class performance in a question-answering dialogue agent","author":"stiff","year":"0","journal-title":"Proc 21th Annu Meeting Special Int Group Discourse Dialogue"},{"key":"ref21","first-page":"217","article-title":"BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance","author":"mccoy","year":"0","journal-title":"Proc 3rd BlackboxNLP Workshop Analyzing Interpreting Neural Netw NLP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5201"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1124"},{"key":"ref26","first-page":"4758","article-title":"Interpreting pretrained contextualized representations via reductions to static embeddings","author":"bommasani","year":"0","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.236"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-1017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2303"},{"key":"ref59","article-title":"Ontonotes release 4.0","author":"weischedel","year":"2011"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1035"},{"key":"ref57","article-title":"Introduction to the CoNLL-2000 shared task chunking","author":"sang","year":"0","journal-title":"Proc 18th Conf Comput Natural Lang Learn"},{"key":"ref56","article-title":"Esslli workshop on distributional lexical semantics bridging the gap between semantic theory and computational simulations","author":"baroni","year":"2008","journal-title":"Assoc Logic Lang Inf"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00016"},{"key":"ref54","article-title":"Attributes in lexical acquisition","author":"almuhareb","year":"2006"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-2002"},{"key":"ref52","first-page":"2690","article-title":"What's in your embedding, and how it predicts task performance","author":"rogers","year":"0","journal-title":"Proc 27th Int Conf Comput Linguistics"},{"key":"ref10","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019"},{"key":"ref11","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"NAACL"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref12","article-title":"XlNet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"yang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","article-title":"Assessing BERT's syntactic abilities","author":"goldberg","year":"2019","journal-title":"arXiv 1901 05287 [cs]"},{"key":"ref14","first-page":"3651","author":"jawahar","year":"2019","journal-title":"ACL"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1241"},{"key":"ref17","first-page":"2324","article-title":"BERT post-training for review reading comprehension and aspect-based sentiment analysis","author":"xu","year":"0","journal-title":"NAACL"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1282"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1630"},{"key":"ref4","first-page":"1081","article-title":"A scalable hierarchical distributed language model","author":"mnih","year":"0","journal-title":"Proc 21st Int Conf Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref6","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"0"},{"key":"ref5","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"collobert","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-2002"},{"key":"ref9","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/365628.365657"},{"key":"ref45","first-page":"136","article-title":"Distributional semantics in technicolor","author":"bruni","year":"0","journal-title":"ACL"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2506"},{"key":"ref47","first-page":"356","article-title":"SemEval-2012 task 2: Measuring degrees of relational similarity","author":"jurgens","year":"0","journal-title":"SemEval"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372094"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-1618"},{"key":"ref44","first-page":"104","article-title":"Better word representations with recursive neural networks for morphology","author":"luong","year":"0","journal-title":"Proc 18th Conf Comput Natural Lang Learn"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1242"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09376654.pdf?arnumber=9376654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:52Z","timestamp":1652194432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9376654\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3065201","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}