{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:44:12Z","timestamp":1770335052118,"version":"3.49.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,10]]},"DOI":"10.1109\/bigdata50022.2020.9377810","type":"proceedings-article","created":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T17:10:21Z","timestamp":1616173821000},"page":"3608-3617","source":"Crossref","is-referenced-by-count":5,"title":["Fine-Tuning Language Models For Semi-Supervised Text Mining"],"prefix":"10.1109","author":[{"given":"Xinyu","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ian","family":"Beaver","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cynthia","family":"Freeman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220090"},{"key":"ref38","article-title":"A broad-coverage challenge corpus for sentence understanding through inference","author":"williams","year":"2017"},{"key":"ref33","article-title":"A classification-based approach to semi-supervised clustering with pairwise constraints","author":"?mieja","year":"2020","journal-title":"Neural Networks"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v088.i07"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.10.016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1004"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.10.022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref34","first-page":"424","article-title":"Probabilistic topic models","volume":"427","author":"steyvers","year":"2007","journal-title":"Handbook of Latent Semantic Analysis"},{"key":"ref10","article-title":"Senteval:An evaluation toolkit for universal sentence representations","author":"conneau","year":"2018"},{"key":"ref40","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","author":"xie","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.advwatres.2011.04.013"},{"key":"ref12","article-title":"Pubmed 200k rct: a dataset for sequential sentence classification in medical abstracts","author":"dernoncourt","year":"2017"},{"key":"ref13","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143892"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/243"},{"key":"ref17","article-title":"Don’t stop pretraining: Adapt language models to domains and tasks","author":"gururangan","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref19","article-title":"Full text of Stack Overflow Q&A about the Python programming language","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref4","first-page":"59","article-title":"A probabilistic framework for semi-supervised clustering","author":"basu","year":"2004","journal-title":"Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4302"},{"key":"ref3","article-title":"Semi-supervised clustering by seeding","author":"basu","year":"2002","journal-title":"Proceedings of 19th International Conference on Machine Learning (ICML-2002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/10\/P10008"},{"key":"ref29","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2133806.2133826"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref2","article-title":"A simple but tough-to-beat baseline for sentence embeddings","author":"arora","year":"2017","journal-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1213"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3223-4_4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052576"},{"key":"ref21","first-page":"361","article-title":"Rcv1: A new benchmark collection for text categorization research","volume":"5","author":"lewis","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref24","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00654"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-019-00723-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"ref25","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"}],"event":{"name":"2020 IEEE International Conference on Big Data (Big Data)","location":"Atlanta, GA, USA","start":{"date-parts":[[2020,12,10]]},"end":{"date-parts":[[2020,12,13]]}},"container-title":["2020 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9377717\/9377728\/09377810.pdf?arnumber=9377810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T11:45:04Z","timestamp":1656330304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9377810\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,10]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/bigdata50022.2020.9377810","relation":{},"subject":[],"published":{"date-parts":[[2020,12,10]]}}}