{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:07:14Z","timestamp":1764785234799,"version":"3.37.3"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1109\/taslp.2023.3337643","type":"journal-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T19:22:11Z","timestamp":1701372131000},"page":"639-650","source":"Crossref","is-referenced-by-count":5,"title":["Lost in Context? On the Sense-Wise Variance of Contextualized Word Embeddings"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8705-9598","authenticated-orcid":false,"given":"Yile","family":"Wang","sequence":"first","affiliation":[{"name":"Institute for AI Industry Research, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5214-2268","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Engineering, Westlake University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"issue":"8","key":"ref2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref3","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"article-title":"RoBERTa: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref4"},{"key":"ref5","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2019"},{"key":"ref6","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan","year":"2020"},{"key":"ref7","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He","year":"2021"},{"key":"ref8","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. 1st Int. Conf. Learn. Representations","author":"Mikolov","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref10","first-page":"4129","article-title":"A structural probe for finding syntax in word representations","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Hewitt","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.383"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref13","article-title":"What do you learn from context? probing for sentence structure in contextualized word representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tenney","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref15","first-page":"743","article-title":"oLMpics-on what language model pre-training captures","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"8","author":"Talmor","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1124"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5201"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.333"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065201"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.blackboxnlp-1.21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.236"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1006"},{"key":"ref24","first-page":"842","article-title":"A primer in BERTology: What we know about how BERT works","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"8","author":"Rogers","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1112"},{"article-title":"Assessing berts syntactic abilities","year":"2019","author":"Goldberg","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1162"},{"key":"ref28","article-title":"Visualizing and measuring the geometry of bert","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Reif","year":"2019"},{"key":"ref29","first-page":"825","article-title":"Lets play mono-poly: BERT can reveal words polysemy level and partitionability into senses","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"9","author":"Soler","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1355"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.365"},{"key":"ref33","first-page":"1012","article-title":"Measuring and improving consistency in pretrained language models","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"9","author":"Elazar","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17609"},{"key":"ref35","first-page":"1","article-title":"SENSEVAL-2: Overview","volume-title":"Proc. SENSEVAL-2 2nd Int. Workshop Evaluating Word Sense Disambiguation Syst.","author":"Edmonds","year":"2001"},{"key":"ref36","first-page":"41","article-title":"The english all-words task","volume-title":"Proc. SENSEVAL-3 3rd Int. Workshop Eval. Syst. Semantic Anal. Text","author":"Snyder","year":"2004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/1621474.1621490"},{"key":"ref38","first-page":"222","article-title":"SemEval-2013 task 12: Multilingual word sense disambiguation","volume-title":"Proc. 2nd Joint Conf. Lexical Comput. Semantics, Volume 2: Proc. 7th Int. Workshop Semantic Eval.","author":"Navigli","year":"2013"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S15-2049"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.423"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18653\/v1\/W18-2501","article-title":"Allen","volume-title":"Proc. Workshop NLP Open Source Softw.","author":"Gardner","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","year":"2016","author":"Wu","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1198"},{"issue":"1","key":"ref50","first-page":"1","article-title":"On the linguistic representational power of neural machine translation models","volume-title":"Comput. Linguistics","volume":"46","author":"Belinkov","year":"2020"},{"key":"ref51","first-page":"171","article-title":"Part-of-speech sequences and distribution in a learner corpus of english","volume-title":"Proc. 13th Res. Comput. Linguistics Conf.","author":"Shih","year":"2000"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1002\/asi.24126"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-020-01533-x"},{"issue":"3","key":"ref54","first-page":"733","article-title":"Position information in transformers: An overview","volume-title":"Comput. Linguistics","volume":"48","author":"Dufter","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.116"},{"article-title":"Technical report on Token Position Bias in Transformers","year":"2023","author":"Amor","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4828"},{"key":"ref58","first-page":"2337","article-title":"Efficient training of BERT by progressively stacking","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Gong","year":"2019"},{"key":"ref59","first-page":"1267","article-title":"WiC: The word-in-context dataset for evaluating context-sensitive meaning representations","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Pilehvar","year":"2019"},{"key":"ref60","article-title":"Superglue: A stickier benchmark for general-purpose language understanding systems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1010"},{"key":"ref62","first-page":"625","article-title":"Neural network acceptability judgments","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"7","author":"Warstadt","year":"2019"},{"issue":"2","key":"ref63","first-page":"313","article-title":"Building a large annotated corpus of english: The penn treebank","volume-title":"Comput. Linguistics","volume":"19","author":"Marcus","year":"1993"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119195"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10333999.pdf?arnumber=10333999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T18:55:45Z","timestamp":1707332145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10333999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3337643","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}