{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T18:04:15Z","timestamp":1785175455619,"version":"3.55.0"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"\n Named Entity Recognition (NER) is fundamental for automating administrative document processing in digital government systems. However, Vietnamese NLP research faces a critical infrastructure gap: existing datasets focus on generic information extraction (news, medical) rather than domain-specific administrative text. We present PAP_NER, the first large-scale, gold-standard Vietnamese administrative NER corpus comprising 162,801 sentences with 205,807 entity annotations across five entity types critical for e-Government workflows: Agency (CQ), Legal Document (VBPL), Object (\u0110T), Datetime (NG), and Quantity (SL). The dataset was constructed through a rigorous human-in-the-loop annotation pipeline, achieving an inter-annotator agreement of\n \n \n \n \n \n \u03ba<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n = 0.85. We demonstrate PAP_NER\u2019s value through comprehensive benchmarking of an established hybrid deep learning architecture, PhoBERT-CRF, which couples monolingual Transformer embeddings (PhoBERT) with Conditional Random Fields for structured prediction. PhoBERT-CRF achieves 97.95% Micro F1-score on the PAP_NER test set, significantly outperforming established baselines: BiLSTM+CRF (+2.01%), multilingual XLM-RoBERTa (+2.52%), and pure Transformer approaches (+0.44%). Ablation analysis reveals that the CRF layer provides statistically significant improvements for structurally complex entities (VBPL:\u2009+\u20090.96%,\n p<\/jats:italic>\n \u2009<\u20090.05, McNemar\u2019s test). We release PAP_NER publicly (DOI:\n 10.5281\/zenodo.18044019<\/jats:ext-link>\n ) under Creative Commons BY 4.0 license to support reproducibility and enable further research in Vietnamese administrative NLP. This work establishes a foundational dataset and methodology for addressing the Vietnamese government NER gap, with implications for low-resource language NLP research.\n <\/jats:p>","DOI":"10.1371\/journal.pone.0353166","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T17:31:47Z","timestamp":1785173507000},"page":"e0353166","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["PAP_NER: A large-scale vietnamese administrative named entity recognition corpus and hybrid deep learning architecture"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4793-9731","authenticated-orcid":true,"given":"Dinh-Dien","family":"La","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tien-Bang","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9210-9164","authenticated-orcid":true,"given":"Ngoc-Huy","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ngoc-Hung","family":"Dang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0075-3427","authenticated-orcid":true,"given":"Trung-Nghia","family":"Phung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3445-2596","authenticated-orcid":true,"given":"Van-Khanh","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,27]]},"reference":[{"key":"pone.0353166.ref001","first-page":"163","volume-title":"Administrative Procedures and Processes","author":"J Ziekow","year":"2021"},{"issue":"6245","key":"pone.0353166.ref002","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1126\/science.aaa8685","article-title":"Advances in natural language processing","volume":"349","author":"J Hirschberg","year":"2015","journal-title":"Science"},{"key":"pone.0353166.ref003","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/978-3-642-45358-8_7","article-title":"Named entity recognition.","volume-title":"Natural language processing of semitic languages","author":"B Mohit","year":"2014"},{"key":"pone.0353166.ref004","unstructured":"Huyen NTM, Luong VX. Vlsp 2016 shared task: Named entity recognition. In: Proceedings of Vietnamese Speech and Language Processing (VLSP). 2016."},{"issue":"4","key":"pone.0353166.ref005","doi-asserted-by":"crossref","first-page":"283","DOI":"10.15625\/1813-9663\/34\/4\/13161","article-title":"VLSP Shared Task: Named Entity Recognition","volume":"34","author":"HTM Nguyen","year":"2019","journal-title":"JCC"},{"issue":"1","key":"pone.0353166.ref006","article-title":"VLSP 2021 - NER Challenge: Named Entity Recognition for Vietnamese","volume":"38","author":"HM Linh","year":"2022","journal-title":"JCSCE"},{"key":"pone.0353166.ref007","doi-asserted-by":"crossref","unstructured":"Truong TH, Dao MH, Nguyen DQ. COVID-19 Named Entity Recognition for Vietnamese. In: Toutanova K, Rumshisky A, Zettlemoyer L, Hakkani-Tur D, Beltagy I, Bethard S, et al., editors. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Online: Association for Computational Linguistics. 2021. p. 2146\u201353.","DOI":"10.18653\/v1\/2021.naacl-main.173"},{"issue":"3","key":"pone.0353166.ref008","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1177\/0261018312458044","article-title":"Public policy futures: A left trilemma?","volume":"33","author":"P Taylor-Gooby","year":"2013","journal-title":"Crit Soc Policy"},{"key":"pone.0353166.ref009","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"pone.0353166.ref010","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"J Devlin","year":"2019"},{"key":"pone.0353166.ref011","article-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","author":"Y Liu","year":"2019","journal-title":"CoRR"},{"key":"pone.0353166.ref012","doi-asserted-by":"crossref","unstructured":"Nguyen DQ, Tuan Nguyen A. PhoBERT: Pre-trained language models for Vietnamese. In: Cohn T, He Y, Liu Y, editors. Findings of the Association for Computational Linguistics: EMNLP 2020. Online: Association for Computational Linguistics. 2020. p. 1037\u201342.","DOI":"10.18653\/v1\/2020.findings-emnlp.92"},{"issue":"15","key":"pone.0353166.ref013","doi-asserted-by":"crossref","first-page":"9789","DOI":"10.24294\/jipd9789","article-title":"Named entity recognition in government domain: A systematic literature review","volume":"8","author":"TW Ramdhani","year":"2024","journal-title":"JIPD"},{"key":"pone.0353166.ref014","first-page":"260","article-title":"Neural Architectures for Named Entity Recognition.","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"G Lample","year":"2016"},{"key":"pone.0353166.ref015","unstructured":"Clark K, Luong MT, Le QV, Manning CD. Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:200310555. 2020."},{"key":"pone.0353166.ref016","unstructured":"Li B, He Y, Xu W. Cross-lingual named entity recognition using parallel corpus: A new approach using xlm-roberta alignment. arXiv preprint arXiv:210111112. 2021."},{"key":"pone.0353166.ref017","doi-asserted-by":"crossref","unstructured":"Hung BT, Huy TQ. Named entity recognition based on combining Pretrained transformer model and deep learning. In: Artificial Intelligence and Sustainable Computing: Proceedings of ICSISCET 2021. Springer; 2022. p. 311\u201320.","DOI":"10.1007\/978-981-19-1653-3_24"},{"key":"pone.0353166.ref018","unstructured":"Lafferty JD, McCallum A, Pereira FCN. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In: Proceedings of the Eighteenth International Conference on Machine Learning. ICML\u201901. San Francisco (CA): Morgan Kaufmann Publishers Inc.; 2001. p. 282\u20139."},{"key":"pone.0353166.ref019","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach. 2020. Available from: https:\/\/openreview.net\/forum?id=SyxS0T4tvS"},{"key":"pone.0353166.ref020","doi-asserted-by":"crossref","first-page":"109309","DOI":"10.1016\/j.compag.2024.109309","article-title":"End-to-end framework for agricultural entity extraction\u2013a hybrid model with transformer","volume":"225","author":"EN Mol","year":"2024","journal-title":"Comput Electron Agric"},{"key":"pone.0353166.ref021","doi-asserted-by":"crossref","first-page":"118385","DOI":"10.1016\/j.eswa.2022.118385","article-title":"A hybrid Transformer approach for Chinese NER with features augmentation","volume":"209","author":"Z Jin","year":"2022","journal-title":"Exp Syst Appl"},{"issue":"2","key":"pone.0353166.ref022","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1080\/01969722.2022.2111506","article-title":"Deep Learning-Based Named Entity Recognition System Using Hybrid Embedding","volume":"55","author":"A Goyal","year":"2024","journal-title":"Cybern Syst"},{"key":"pone.0353166.ref023","article-title":"UE-NER-2025: A GPT-based approach to named entity recognition on Urdu and English","author":"M Ahmad","year":"2025","journal-title":"IEEE Access"},{"key":"pone.0353166.ref024","unstructured":"Ullah S, et al. EDU-NER-2025: Named Entity Recognition in Urdu Educational Texts using XLM-RoBERTa. arXiv preprint arXiv:250418142. 2025."},{"issue":"2","key":"pone.0353166.ref025","first-page":"35","article-title":"E-Government Architecture in Developing Countries: A Case of Public Entities in Vietnam","volume":"14","author":"TT Nguyen","year":"2022","journal-title":"Int J eBus eGovernment Stud"},{"key":"pone.0353166.ref026","doi-asserted-by":"crossref","unstructured":"Nguyen DQ, Nguyen DQ, Vu T, Dras M, Johnson M. A Fast and Accurate Vietnamese Word Segmenter. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). Miyazaki, Japan: European Language Resources Association (ELRA); 2018. p. 10\u20137.","DOI":"10.63317\/32m47vrkp2wj"},{"key":"pone.0353166.ref027","first-page":"56","article-title":"VnCoreNLP: A Vietnamese Natural Language Processing Toolkit.","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations","author":"T Vu","year":"2018"},{"issue":"1","key":"pone.0353166.ref028","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A Coefficient of Agreement for Nominal Scales","volume":"20","author":"J Cohen","year":"1960","journal-title":"Educ Psychol Meas"},{"key":"pone.0353166.ref029","unstructured":"Nguyen DQ, Nguyen LT, Tran C, Nguyen D\u00e2n, Phung D, Bui H. Phogpt: Generative pre-training for vietnamese. arXiv preprint arXiv:231102945. 2023."},{"key":"pone.0353166.ref030","unstructured":"Nguyen Q, Pham H, Dao D. Vinallama: Llama-based vietnamese foundation model. arXiv preprint arXiv:231211011. 2023."},{"issue":"2","key":"pone.0353166.ref031","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/BF02295996","article-title":"Note on the sampling error of the difference between correlated proportions or percentages","volume":"12","author":"Q McNEMAR","year":"1947","journal-title":"Psychometrika"},{"key":"pone.0353166.ref032","doi-asserted-by":"crossref","unstructured":"Li X, Feng J, Meng Y, Han Q, Wu F, Li J. A Unified MRC Framework for Named Entity Recognition. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020. p. 5849\u201359.","DOI":"10.18653\/v1\/2020.acl-main.519"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T17:31:52Z","timestamp":1785173512000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353166"}},"subtitle":[],"editor":[{"given":"Asif","family":"Ekbal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":32,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0353166","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,27]]}}}