{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:36:56Z","timestamp":1772933816691,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11400885","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"3038-3044","source":"Crossref","is-referenced-by-count":0,"title":["Comprehensive Evaluation of Transformer Models for Multilingual PII Detection"],"prefix":"10.1109","author":[{"given":"Divya","family":"Singh","sequence":"first","affiliation":[{"name":"Hitachi Ltd.,Digital Infrastructure Innovation Center,Tokyo,Japan"}]},{"given":"Satoru","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Hitachi Ltd.,Digital Infrastructure Innovation Center,Tokyo,Japan"}]},{"given":"Kunju","family":"Kashalikar","sequence":"additional","affiliation":[{"name":"Hitachi Vantara,Pentaho SW,San Francisco,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"European Parliament and Council of the European Union","volume-title":"General Data Protection Regulation (GDPR)","year":"2016"},{"key":"ref2","article-title":"California State Legislature","volume-title":"California Consumer Privacy Act (CCPA)","year":"2018"},{"key":"ref3","volume-title":"Act on the Protection of Personal Information (APPI)","year":"2003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/07421222.1996.11518099"},{"key":"ref5","article-title":"A Morphology of the Organisation of Data Governance","volume-title":"ECIS 2011 Proceedings","author":"Otto","year":"2011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2013.04.004"},{"key":"ref7","volume-title":"Mastering Regular Expressions","author":"Friedl","year":"2006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.4324\/9780203461891-3"},{"key":"ref9","article-title":"The Digitization of the World from Edge to Core","author":"Gantz","year":"2021","journal-title":"IDC"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-1178"},{"key":"ref11","first-page":"4411","article-title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML)","author":"Hu","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1493","volume-title":"How multilingual is Multilingual BERT?","author":"Pires","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/DELCON64804.2024.10866085"},{"key":"ref16","volume-title":"Faker"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-021-01317-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/09727531221146825"},{"key":"ref21","article-title":"KLUE: Korean Language Understanding Evaluation","author":"Park","year":"2021","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3675888.3676036"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-6088-8_56"},{"key":"ref24","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Training Compute-Optimal Large Language Models","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45563-x"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10825282"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119195"},{"key":"ref30","volume-title":"MeCab: Yet Another Part-of-Speech and Morphological Analyzer","author":"Kudo","year":"2006"},{"key":"ref31","article-title":"KoNLPy: Korean NLP in Python","volume-title":"Proceedings of the Annual Conference on Human and Cognitive Language Technology","author":"Park","year":"2014"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.7202\/1060169ar"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11400885.pdf?arnumber=11400885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:52:34Z","timestamp":1772866354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11400885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11400885","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}