{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:34:45Z","timestamp":1763202885882,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T00:00:00Z","timestamp":1709510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Australian Research Council","award":["DP220103717"],"award-info":[{"award-number":["DP220103717"]}]},{"name":"National Science Foundation of China","award":["62072257"],"award-info":[{"award-number":["62072257"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"DOI":"10.1145\/3616855.3635849","type":"proceedings-article","created":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T18:18:12Z","timestamp":1709576292000},"page":"18-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["IDoFew: Intermediate Training Using Dual-Clustering in Language Models for Few Labels Text Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1595-9225","authenticated-orcid":false,"given":"Abdullah","family":"Alsuhaibani","sequence":"first","affiliation":[{"name":"University of Technology Sydney & Islamic University of Madinah, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8146-336X","authenticated-orcid":false,"given":"Hamad","family":"Zogan","sequence":"additional","affiliation":[{"name":"University of Technology Sydney & Jazan University, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3930-6600","authenticated-orcid":false,"given":"Imran","family":"Razzak","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7534-3313","authenticated-orcid":false,"given":"Shoaib","family":"Jameel","sequence":"additional","affiliation":[{"name":"University of Southampton, Southampton, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4493-6663","authenticated-orcid":false,"given":"Guandong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, Australia"}]}],"member":"320","published-online":{"date-parts":[[2024,3,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2034691.2034742"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"e_1_3_2_2_3_1","first-page":"993","article-title":"Latent dirichlet allocation","author":"Blei David M","year":"2003","unstructured":"David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research 3, Jan (2003), 993--1022.","journal-title":"Journal of machine Learning research 3"},{"volume-title":"Advances in Web Mining and Web Usage Analysis","author":"Bloehdorn Stephan","key":"e_1_3_2_2_4_1","unstructured":"Stephan Bloehdorn and Andreas Hotho. 2006. Boosting for Text Classification with Semantic Features. In Advances in Web Mining and Web Usage Analysis, Bamshad Mobasher, Olfa Nasraoui, Bing Liu, and Brij Masand (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 149--166."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2015974"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.118"},{"key":"e_1_3_2_2_7_1","unstructured":"Leshem Choshen Elad Venezian Shachar Don-Yehia Noam Slonim and Yoav Katz. 2022. Where to start? Analyzing the potential value of intermediate models. arxiv: 2211.00107 [cs.CL]"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i10.7158"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19--1423"},{"key":"e_1_3_2_2_10_1","volume-title":"Self-training improves pre-training for natural language understanding. arXiv preprint arXiv:2010.02194","author":"Du Jingfei","year":"2020","unstructured":"Jingfei Du, Edouard Grave, Beliz Gunel, Vishrav Chaudhary, Onur Celebi, Michael Auli, Ves Stoyanov, and Alexis Conneau. 2020. Self-training improves pre-training for natural language understanding. arXiv preprint arXiv:2010.02194 (2020)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Liat Ein-Dor Eyal Shnarch Lena Dankin Alon Halfon Benjamin Sznajder Ariel Gera Carlos Alzate Martin Gleize Leshem Choshen Yufang Hou Yonatan Bilu Ranit Aharonov and Noam Slonim. 2020. Corpus Wide Argument Mining - a Working Solution. In AAAI.","DOI":"10.1609\/aaai.v34i05.6270"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the First International Conference on Knowledge Discovery and Data Mining (Montr\u00e9al","author":"Feldman Ronen","year":"1995","unstructured":"Ronen Feldman and Ido Dagan. 1995. Knowledge Discovery in Textual Databases (KDT). In Proceedings of the First International Conference on Knowledge Discovery and Data Mining (Montr\u00e9al, Qu\u00e9bec, Canada) (KDD'95). AAAI Press, 112--117."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016407"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.206"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44230-022-00012-0"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.813"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113288"},{"key":"e_1_3_2_2_19_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.391"},{"key":"e_1_3_2_2_21_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-1777-5_24"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1218990"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219855"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.467"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.05.028"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"e_1_3_2_2_30_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arxiv","author":"Sanh Victor","year":"1910","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2020. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arxiv: 1910.01108 [cs.CL]"},{"key":"e_1_3_2_2_31_1","volume-title":"The 2022 Conference on Empirical Methods in Natural Language Processing","author":"Schick Timo","year":"2020","unstructured":"Timo Schick and Hinrich Sch\u00fctze. 2020. Exploiting cloze questions for few shot text classification and natural language inference. The 2022 Conference on Empirical Methods in Natural Language Processing (2020)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1177\/0022022114557479"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2095"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.526"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00456"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564401"},{"key":"e_1_3_2_2_37_1","volume-title":"Matching the blanks: Distributional similarity for relation learning. ACL","author":"Soares Livio Baldini","year":"2019","unstructured":"Livio Baldini Soares, Nicholas FitzGerald, Jeffrey Ling, and Tom Kwiatkowski. 2019. Matching the blanks: Distributional similarity for relation learning. ACL (2019)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1045"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.221"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.170"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.219"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W15-1509"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2109.04707"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.84"},{"key":"e_1_3_2_2_45_1","volume-title":"Garnett (Eds.)","volume":"28","author":"Zhang Xiang","year":"2015","unstructured":"Xiang Zhang, Junbo Zhao, and Yann LeCun. 2015. Character-level Convolutional Networks for Text Classification. In Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett (Eds.), Vol. 28. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2015\/file\/250cf8b51c773f3f8dc8b4be867a9a02-Paper.pdf"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00389"}],"event":{"name":"WSDM '24: The 17th ACM International Conference on Web Search and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Merida Mexico","acronym":"WSDM '24"},"container-title":["Proceedings of the 17th ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635849","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3616855.3635849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:48:05Z","timestamp":1755823685000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,4]]},"references-count":46,"alternative-id":["10.1145\/3616855.3635849","10.1145\/3616855"],"URL":"https:\/\/doi.org\/10.1145\/3616855.3635849","relation":{},"subject":[],"published":{"date-parts":[[2024,3,4]]},"assertion":[{"value":"2024-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}