{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:14:54Z","timestamp":1758586494400,"version":"3.44.0"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100020901","name":"Islamic University of Madinah","doi-asserted-by":"publisher","award":["research group (first) project no. 956"],"award-info":[{"award-number":["research group (first) project no. 956"]}],"id":[{"id":"10.13039\/501100020901","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Navigating legal texts like a national constitution is notoriously difficult due to specialized jargon and complex internal references. For the Constitution of Pakistan, no automated, user-friendly search tool existed to address this challenge. This paper introduces ULBERT, a novel AI-powered information retrieval framework designed to make the constitution accessible to all users, from legal experts to ordinary citizens, in both English and Urdu.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>The system is built around a custom AI model that moves beyond keyword matching to understand the semantic meaning of a user's query. It processes questions in English or Urdu and compares them to the constitutional text, identifying the most relevant passages based on contextual and semantic similarity.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In performance testing, the ULBERT framework proved highly effective. It successfully retrieved the correct constitutional information with an accuracy of 86% for English queries and 73% for Urdu queries.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>These results demonstrate a significant breakthrough in enhancing the accessibility of foundational legal documents through artificial intelligence. The framework provides an effective and intuitive tool for legal inquiry, empowering a broader audience to understand the Constitution of Pakistan.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fdata.2025.1448785","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T04:12:24Z","timestamp":1758514344000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ULBERT: a domain-adapted BERT model for bilingual information retrieval from Pakistan's constitution"],"prefix":"10.3389","volume":"8","author":[{"given":"Qaiser","family":"Abbas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Waqas","family":"Nawaz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sadia","family":"Niazi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Awais","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nllp-1.31","article-title":"\u201cAralegal-bert: a pretrained language model for arabic legal text,\u201d","author":"Al-qurishi","year":"2022","journal-title":"Proceedings of the Natural Legal Language Processing Workshop 2022"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1109\/SYNASC65383.2024.00054","article-title":"\u201cThe NLP for employee review sentiment analysis: an explainable perspective,\u201d","author":"Babic","year":"2024","journal-title":"2024 26th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)"},{"key":"B3","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","article-title":"Enriching word vectors with subword information","volume":"5","author":"Bojanowski","year":"2017","journal-title":"Trans. Assoc. Comput. Linguist"},{"key":"B4","doi-asserted-by":"crossref","first-page":"216","DOI":"10.4337\/9781788972826.00017","article-title":"\u201cLexnlp: natural language processing and information extraction for legal and regulatory texts,\u201d","volume-title":"Research Handbook On Big Data Law","author":"Bommarito II","year":"2021"},{"key":"B5","article-title":"Legal-bert: The muppets straight out of law school","author":"Chalkidis","year":"2020","journal-title":"arXiv preprint arXiv:2010.02559"},{"key":"B6","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.patrec.2021.04.029","article-title":"Ring-regularized cosine similarity learning for fine-grained face verification","volume":"148","author":"Chen","year":"2021","journal-title":"Pattern Recognit. Lett"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1002\/asi.24619","article-title":"A retrieval model family based on the probability ranking principle for ad hoc retrieval","volume":"73","author":"Dang","year":"2022","journal-title":"J. Assoc. Inf. Sci. Technol"},{"key":"B8","first-page":"1708","article-title":"Bidirectional encoder representations from transformers (bert) language model for sentiment analysis task","volume":"12","author":"Deepa","year":"2021","journal-title":"Turkish J. Comput. Mathem. Educ"},{"key":"B9","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"B10","doi-asserted-by":"publisher","first-page":"4997","DOI":"10.32604\/cmc.2024.054459","article-title":"Cyberbullying sexism harassment identification by metaheurustics-tuned extreme gradient boosting","volume":"80","author":"Dobrojevic","year":"2024","journal-title":"Comput. Mater. Continua"},{"key":"B11","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1016\/j.jbusres.2022.01.065","article-title":"Search engine optimization: the long-term strategy of keyword choice","volume":"144","author":"Erdmann","year":"2022","journal-title":"J. Bus. Res"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1101\/2022.03.05.22271961","article-title":"Mining for health: a comparison of word embedding methods for analysis of ehrs data","author":"Getzen","year":"2022","journal-title":"medRxiv.2022\u201303"},{"key":"B13","doi-asserted-by":"publisher","first-page":"187","DOI":"10.3390\/info14030187","article-title":"A systematic review of transformer-based pre-trained language models through self-supervised learning","volume":"14","author":"Kotei","year":"2023","journal-title":"Information"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1017\/9781108684163","author":"Leskovec","year":"2020","journal-title":"Mining of Massive Data Sets"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42979-021-00467-1","article-title":"Deep neural network (DNN) solution for real-time detection of distributed denial of service (DDOS) attacks in software defined networks (SDNS)","volume":"2","author":"Makuvaza","year":"2021","journal-title":"SN Comput. Sci"},{"key":"B16","doi-asserted-by":"publisher","first-page":"101606","DOI":"10.1016\/j.jksuci.2023.101606","article-title":"Contextual embeddings based on fine-tuned urdu-bert for urdu threatening content and target identification","volume":"35","author":"Malik","year":"2023","journal-title":"J. King Saud Univ. Comput. Inf. Sci"},{"key":"B17","doi-asserted-by":"crossref","first-page":"22","DOI":"10.2991\/978-94-6463-482-2_3","article-title":"\u201cEmployee reviews sentiment classification using bert encoding and adaboost classifier tuned by modified pso algorithm,\u201d","volume-title":"Proceedings of the 2nd International Conference on Innovation in Information Technology and Business (ICIITB 2024)","author":"Markovic","year":"2024"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.nllp-1.8","article-title":"\u201cJurbert: a romanian bert model for legal judgement prediction,\u201d","author":"Masala","year":"2021","journal-title":"Proceedings of the Natural Legal Language Processing Workshop 2021"},{"key":"B19","article-title":"\u201cDistributed representations of words and phrases and their compositionality,\u201d","author":"Mikolov","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B20","doi-asserted-by":"publisher","first-page":"25731","DOI":"10.1038\/s41598-024-77240-w","article-title":"Sentiment classification for insider threat identification using metaheuristic optimized machine learning classifiers","volume":"14","author":"Mladenovic","year":"2024","journal-title":"Sci. Rep"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1145\/3487552.3487862","article-title":"\u201cMeasuring the network performance of google cloud platform,\u201d","author":"Mok","year":"2021","journal-title":"Proceedings of the 21st ACM Internet Measurement Conference"},{"key":"B22","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/s40747-021-00517-4","article-title":"Machine learning-driven automatic storage space recommendation for object-based cloud storage system","volume":"81","author":"Mondal","year":"2021","journal-title":"Complex Intell. Syst"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162","article-title":"\u201cGlove: global vectors for word representation,\u201d","author":"Pennington","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202","article-title":"\u201cDeep contextualized word representations,\u201d","author":"Peters","year":"2018","journal-title":"Proceedings of NAACL-HLT"},{"key":"B25","doi-asserted-by":"crossref","first-page":"5696","DOI":"10.3390\/app14135696","article-title":"A comprehensive analysis of various tokenizers for arabic large language models","volume":"14","author":"Qarah","year":"2024","journal-title":"Appl. Sci."},{"key":"B26","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"B27","first-page":"1","article-title":"Latent semantic indexing: an overview","volume":"240","author":"Rosario","year":"2000","journal-title":"Techn. Rep. INFOSYS"},{"key":"B28","first-page":"721","article-title":"\u201cContrastive study of simple pagerank, hits and weighted pagerank algorithms,\u201d","volume-title":"2017 7th International Conference on Cloud Computing, Data Science &Engineering-Confluence","author":"Sen","year":"2017"},{"key":"B29","unstructured":"Shehzaad Nakhoda\n              Z. U.\n            \n          \n          The constitution of the islamic republic of Pakistan\n          \n          1973"},{"key":"B30","article-title":"On the semantic interpretability of artificial intelligence models","author":"Silva","year":"2019","journal-title":"arXiv preprint arXiv:1907.04105"},{"key":"B31","first-page":"35","article-title":"Modern information retrieval: a brief overview","volume":"24","author":"Singhal","year":"2001","journal-title":"IEEE Data Eng. Bull"},{"key":"B32","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1007\/s42979-025-04122-x","article-title":"Detecting harassment in user comments: two-tier machine learning and metaheuristics approach with natural language processing","volume":"6","author":"Todorovic","year":"2025","journal-title":"SN Comput. Sci"},{"key":"B33","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/s10506-022-09319-6","article-title":"Sm-bert-cr: a deep learning approach for case law retrieval with supporting model","volume":"31","author":"Vuong","year":"2023","journal-title":"Artif. Intell. Law"},{"key":"B34","first-page":"1","article-title":"\u201cA theoretical analysis of normalized discounted cumulative gain (NDCG) ranking measures,\u201d","volume-title":"Proceedings of the 26th Annual Conference on Learning Theory (COLT 2013)","author":"Wang","year":"2023"},{"key":"B35","volume-title":"A Brief History of Pakistan","author":"Wynbrandt","year":"2009"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2025.1448785\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T04:12:28Z","timestamp":1758514348000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2025.1448785\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":35,"alternative-id":["10.3389\/fdata.2025.1448785"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2025.1448785","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"article-number":"1448785"}}