{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T01:11:52Z","timestamp":1754183512083,"version":"3.41.2"},"reference-count":24,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2025,8,1]]},"DOI":"10.1587\/transinf.2024dat0003","type":"journal-article","created":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T17:11:29Z","timestamp":1736183489000},"page":"872-882","source":"Crossref","is-referenced-by-count":0,"title":["Pre-trained BERT Model Retrieval: Inference-Based No-Learning Approach using k-Nearest Neighbour Algorithm"],"prefix":"10.1587","volume":"E108.D","author":[{"given":"Huu-Long","family":"PHAM","sequence":"first","affiliation":[{"name":"Graduate School of Information Science, University of Hyogo"}]},{"given":"Ryota","family":"MIBAYASHI","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science, University of Hyogo"}]},{"given":"Takehiro","family":"YAMAMOTO","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science, University of Hyogo"}]},{"given":"Makoto P.","family":"KATO","sequence":"additional","affiliation":[{"name":"Faculty of Library, Information and Media Science, University of Tsukuba"}]},{"given":"Yusuke","family":"YAMAMOTO","sequence":"additional","affiliation":[{"name":"School of Data Science, Nagoya City University"}]},{"given":"Yoshiyuki","family":"SHOJI","sequence":"additional","affiliation":[{"name":"Faculty of Informatics, Shizuoka University"}]},{"given":"Hiroaki","family":"OHSHIMA","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science, University of Hyogo"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, \u201cBERT: Pre-training of deep bidirectional transformers for language understanding,\u201d Proc. 2019 Conference of the North American Chapter of the Association for Computational Linguistics, pp.4171-4186, June 2019. 10.18653\/v1\/n19-1423"},{"key":"2","unstructured":"[2] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, Aidan N. Gomez, \u0141. Kaiser, and I. Polosukhin, \u201cAttention is All you Need,\u201d Proc. 31st Int. Conf. Neural Information Processing Systems, pp.6000-6010, 2017."},{"key":"3","unstructured":"[3] Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov, \u201cRoBERTa: A Robustly optimized BERT Pretraining Approach,\u201d arXiv:1907.11692, 2019."},{"key":"4","unstructured":"[4] Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma, and R. Soricut, \u201cALBERT: A Lite BERT for Self-supervised Learning of Language Representations,\u201d arXiv preprint arXiv:1909.11942, 2019."},{"key":"5","unstructured":"[5] P. He, X. Liu, J. Gao, and W. Chen, \u201cDeberta: Decoding-enhanced bert with disentangled attention,\u201d arXiv preprint arXiv:2006.03654, 2020."},{"key":"6","unstructured":"[6] V. Sanh, L. Debut, J. Chaumond, and T. Wolf, \u201cDistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter,\u201d arXiv preprint arXiv:1910.01108, 2019."},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] I. Beltagy, K. Lo, and A. Cohan, \u201cSciBERT: A pretrained language model for scientific text,\u201d Proc. 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp.3615-3620, Nov. 2019. 10.18653\/v1\/d19-1371","DOI":"10.18653\/v1\/D19-1371"},{"key":"8","unstructured":"[8] D. Araci, \u201cFinBERT: Financial Sentiment Analysis with Pre-trained Language Models,\u201d arXiv preprint arXiv:1908.10063, 2019."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] T. Caselli, V. Basile, Jelena Mitrovi\u0107, and M. Granitzer, \u201cHateBERT: Retraining BERT for Abusive Language Detection in English,\u201d Proc. 5th Workshop on Online Abuse and Harms, Aug. 2021. 10.18653\/v1\/2021.woah-1.3","DOI":"10.18653\/v1\/2021.woah-1.3"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] I. Chalkidis, M. Fergadiotis, P. Malakasiotis, N. Aletras, and I. Androutsopoulos, \u201cLEGAL-BERT: The muppets straight out of law school,\u201d Proc. 2020 Conference on Empirical Methods in Natural Language Processing, pp.2898-2904, Nov. 2020. 10.18653\/v1\/2020.findings-emnlp.261","DOI":"10.18653\/v1\/2020.findings-emnlp.261"},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] J. Lee, W. Yoon, S. Kim, D. Kim, S. Kim, C. So, and J. Kang, \u201cBioBERT: a pre-trained biomedical language representation model for biomedical text mining,\u201d Bioinformatics, vol.36, no.4, pp.1234-1240, Sept. 2019. 10.1093\/bioinformatics\/btz682","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"12","unstructured":"[12] K. Huang, J. Altosaar, and R. Ranganath, \u201cClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission,\u201d arXiv:1904.05342, 2019."},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] L. Rasmy, Y. Xiang, Z. Xie, C. Tao, and D. Zhi, \u201cMed-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction,\u201d npj Digital Medicine, vol.4, no.1, 2021. 10.1038\/s41746-021-00455-y","DOI":"10.1038\/s41746-021-00455-y"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] T. Chakrabarty, C. Hidey, and K. McKeown, \u201cIMHO fine-tuning improves claim detection,\u201d Proc. 2019 Conference of the North American Chapter of the Association for Computational Linguistics, pp.558-563, June 2019. 10.18653\/v1\/n19-1054","DOI":"10.18653\/v1\/N19-1054"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] D.Q. Nguyen, T. Vu, and A.T. Nguyen, \u201cBERTweet: A pre-trained language model for English Tweets,\u201d Proc. 2020 Conference on Empirical Methods in Natural Language Processing, pp.9-14, Oct. 2020. 10.18653\/v1\/2020.emnlp-demos.2","DOI":"10.18653\/v1\/2020.emnlp-demos.2"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] X. Han and J. Eisenstein, \u201cUnsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling,\u201d Proc. 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp.4238-4248, Nov. 2019. 10.18653\/v1\/d19-1433","DOI":"10.18653\/v1\/D19-1433"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] M.P. Kato, H. Ohshima, Y.-H. Liu, and H.-L. Chen, \u201cA test collection for ad-hoc dataset retrieval,\u201d Proc. 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp.2450-2456, 2021. 10.1145\/3404835.3463261","DOI":"10.1145\/3404835.3463261"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] E. Kacprzak, L.M. Koesten, L.-D. Ib\u00e1\u00f1ez, E. Simperl, and J. Tennison, \u201cA query log analysis of dataset search. In Web Engineering, pp.429-436, 2017. 10.1007\/978-3-319-60131-1_29","DOI":"10.1007\/978-3-319-60131-1_29"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] K. Gregory, P. Groth, H. Cousijn, A. Scharnhorst, and S. Wyatt, \u201cSearching data: A review of observational data retrieval practices,\u201d Journal of the Association for Information Science and Technology, 70, 07 2017.","DOI":"10.1002\/asi.24165"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] D. Kern and B. Mathiak, \u201cAre there any differences in data set retrieval compared to well-known literature retrieval?,\u201d TPDL, vol.9316, pp.197-208, 09 2015. 10.1007\/978-3-319-24592-8_15","DOI":"10.1007\/978-3-319-24592-8_15"},{"key":"21","unstructured":"[21] M.R. Karimi, Nezihe Merve G\u00fcrel, Bojan Karla\u0161, J. Rausch, C. Zhang, and A. Krause, \u201cOnline active model selection for pre-trained classifiers,\u201d Int. Conf. Artificial Intelligence and Statistics, pp.307-315, 2021."},{"key":"22","unstructured":"[22] K. You, Y. Liu, J. Wang, and M. Long, \u201cLogme: Practical assessment of pre-trained models for transfer learning,\u201d Int. Conf. Machine Learning, pp.12133-12143, 2021."},{"key":"23","doi-asserted-by":"publisher","unstructured":"[23] L. Zou, W. Lu, Y. Liu, H. Cai, X. Chu, D. Ma, D. Shi, Y. Sun, Z. Cheng, S. Gu, S. Wang, and D. Yin, \u201cPre-trained language model-based retrieval and ranking for web search,\u201d ACM Transactions on the Web, vol.17, no.1, pp.1-36, dec 2022. 10.1145\/3568681","DOI":"10.1145\/3568681"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] C. Burges, T. Shaked, E. Renshaw, A. Lazier, M. Deeds, N. Hamilton, and G. Hullender, \u201cLearning to rank using gradient descent,\u201d Proc. 22nd Int. Conf. Machine Learning, pp.89-96, 2005. 10.1145\/1102351.1102363","DOI":"10.1145\/1102351.1102363"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/8\/E108.D_2024DAT0003\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T03:28:54Z","timestamp":1754105334000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/8\/E108.D_2024DAT0003\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,1]]},"references-count":24,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024dat0003","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2025,8,1]]},"article-number":"2024DAT0003"}}