{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:19:04Z","timestamp":1783009144590,"version":"3.54.5"},"reference-count":60,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hong Kong Shue Yan University","award":["Later"],"award-info":[{"award-number":["Later"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>The rapid growth of digital content in Urdu has created an urgent need for effective automatic text summarization (ATS) systems. While extractive methods have been widely studied, abstractive summarization for Urdu remains largely unexplored due to the language\u2019s complex morphology and rich literary tradition. This paper systematically evaluates four transformer-based language models (BERT-Urdu, BART, mT5, and GPT-2) for Urdu abstractive summarization, comparing their performance against conventional machine learning and deep learning approaches. Using multiple Urdu datasets\u2014including the Urdu Summarization Corpus, Fake News Dataset, and Urdu-Instruct-News\u2014we show that fine-tuned Transformer Language Models (TLMs) consistently outperform traditional methods, with the multilingual mT5 model achieving a 0.42 absolute improvement in F1-score over the best baseline. Our analysis reveals that mT5\u2019s architecture is particularly effective at handling Urdu-specific challenges such as right-to-left script processing, diacritic interpretation, and complex verb\u2013noun compounding. Furthermore, we present empirically validated hyperparameter configurations and training strategies for Urdu ATS, establishing transformer-based approaches as the new state-of-the-art for Urdu summarization. Notably, mT5 outperforms Seq2Seq baselines by up to 20% in ROUGE-L, underscoring the efficacy of Transformer-based models for low-resource languages. This work contributes both a systematic review of prior research and a novel empirical benchmark for advancing Urdu abstractive summarization.<\/jats:p>","DOI":"10.3390\/info16090784","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T09:32:01Z","timestamp":1757496721000},"page":"784","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A Systematic Review and Experimental Evaluation of Classical and Transformer-Based Models for Urdu Abstractive Text Summarization"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3687-0270","authenticated-orcid":false,"given":"Muhammad","family":"Azhar","sequence":"first","affiliation":[{"name":"Department of Applied Data Science, Hong Kong Shue Yan University, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adeen","family":"Amjad","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Comsats University Islamabad, Islamabad 45550, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1488-7696","authenticated-orcid":false,"given":"Deshinta Arrova","family":"Dewi","sequence":"additional","affiliation":[{"name":"Faculty of Data Science and Information Technology, INTI International University, Nilai 71800, Negeri Sembilan, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4180-4377","authenticated-orcid":false,"given":"Shahreen","family":"Kasim","sequence":"additional","affiliation":[{"name":"Faculty of Computer Sciences and Information Technology, Universiti Tun Hussain Onn Malaysia, Jalan Persiaran Tun Dr. Ismail, Parit Raja 86400, Johor, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Saggion, H., and Poibeau, T. (2013). Automatic Text Summarization: Past, Present and Future. Multi-Source, Multilingual Information Extraction and Summarization, Springer.","DOI":"10.1007\/978-3-642-28569-1_1"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Rahul, S., Rauniyar, S. (2020, January 26\u201328). A Survey on Deep Learning Based Various Methods Analysis of Text Summarization. Proceedings of the 2020 International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India.","DOI":"10.1109\/ICICT48043.2020.9112474"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Bhatti, M.W., and Aslam, M. (2019, January 21\u201322). ISUTD: Intelligent System for Urdu Text De-Summarization. Proceedings of the 2019 International Conference on Engineering and Emerging Technologies (ICEET), Lahore, Pakistan.","DOI":"10.1109\/CEET1.2019.8711842"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"108670","DOI":"10.1016\/j.asoc.2022.108670","article-title":"An Approach for Extractive Text Summarization Using Fuzzy Evolutionary and Clustering Algorithms","volume":"120","author":"Verma","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Fejer, H.N., and Omar, N. (2014, January 18\u201320). Automatic Arabic Text Summarization Using Clustering and Keyphrase Extraction. Proceedings of the 6th International Conference on Information Technology and Multimedia, Putrajaya, Malaysia.","DOI":"10.1109\/ICIMU.2014.7066647"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"13248","DOI":"10.1109\/ACCESS.2021.3052783","article-title":"A Survey of the State-of-the-Art Models in Neural Abstractive Text Summarization","volume":"9","author":"Syed","year":"2021","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Siragusa, G., and Robaldo, L. (2022). Sentence Graph Attention For Content-Aware Summarization. Appl. Sci., 12.","DOI":"10.3390\/app122010382"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Allahyari, M., Pouriyeh, S., Assefi, M., Safaei, S., Trippe, E.D., Gutierrez, J.B., and Kochut, K. (2017). Text Summarization Techniques: A Brief Survey. arXiv.","DOI":"10.14569\/IJACSA.2017.081052"},{"key":"ref_9","unstructured":"Witte, R., Krestel, R., and Bergler, S. (2007, January 26\u201327). Generating Update Summaries for DUC 2007. Proceedings of the Document Understanding Conference, Rochester, NY, USA."},{"key":"ref_10","unstructured":"Rahman, T. (2004, January 15\u201321). Language Policy and Localization in Pakistan: Proposal for a Paradigmatic Shift. Proceedings of the SCALLA Conference on Computational Linguistics, Seoul, Republic of Korea."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Janjanam, P., and Reddy, C.P. (2019, January 21\u201323). Text Summarization: An Essential Study. Proceedings of the 2019 International Conference on Computational Intelligence in Data Science (ICCIDS), Chennai, India.","DOI":"10.1109\/ICCIDS.2019.8862030"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1186\/s40537-020-00386-7","article-title":"Arabic Text Summarization Using Deep Learning Approach","volume":"7","author":"Desouki","year":"2020","journal-title":"J. Big Data"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Vogel-Fernandez, A., Calleja, P., and Rico, M. (2022). esT5s: A Spanish Model for Text Summarization. Towards a Knowledge-Aware AI, IOS Press.","DOI":"10.3233\/SSW220020"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"04002","DOI":"10.1051\/e3sconf\/202339904002","article-title":"Text Summarization and Translation of Summarized Outcome in French","volume":"Volume 399","author":"Vetriselvi","year":"2023","journal-title":"E3S Web of Conferences"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1791","DOI":"10.47738\/jads.v6i3.702","article-title":"A Study of Unified Framework for Extremism Classification, Ideology Detection, Propaganda Analysis, and Flagged Data Detection Using Transformers","volume":"6","author":"Balajia","year":"2025","journal-title":"J. Appl. Data Sci."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Camastra, F., and Razi, G. (2020). Italian Text Categorization with Lemmatization and Support Vector Machines. Neural Approaches to Dynamics of Signal Exchanges, Springer.","DOI":"10.1007\/978-981-13-8950-4_5"},{"key":"ref_17","unstructured":"Garcia, G.L., Paiola, P.H., Jodas, D.S., Sugi, L.A., and Papa, J.P. (2024, January 12\u201315). Text Summarization and Temporal Learning Models Applied to Portuguese Fake News Detection in a Novel Brazilian Corpus Dataset. Proceedings of the 16th International Conference on Computational Processing of Portuguese, Santiago de Compostela, Spain."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Goloviznina, V., and Kotelnikov, E. (2022). Automatic Summarization of Russian Texts: Comparison of Extractive and Abstractive Methods. arXiv.","DOI":"10.28995\/2075-7182-2022-21-223-235"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Xiong, C., Wang, Z., Shen, L., and Deng, N. (2020). TF-BiLSTMS2S: A Chinese Text Summarization Model. Advanced Information Networking and Applications: Proceedings of the 34th International Conference on Advanced Information Networking and Applications (AINA-2020), Caserta, Italy, 15\u201317 April 2020, Springer International Publishing.","DOI":"10.1007\/978-3-030-44041-1_22"},{"key":"ref_20","unstructured":"Nagai, Y., Oka, T., and Komachi, M. (2024, January 20\u201325). A Document-Level Text Simplification Dataset for Japanese. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Torino, Italy."},{"key":"ref_21","unstructured":"Naseer, A., and Hussain, S. (2009). Supervised Word Sense Disambiguation for Urdu Using Bayesian Classification. Technical Report, Center for Research in Urdu Language Processing."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/s10462-016-9482-x","article-title":"Urdu Language Processing: A Survey","volume":"47","author":"Daud","year":"2017","journal-title":"Artif. Intell. Rev."},{"key":"ref_23","unstructured":"Ramos, J. (2003, January 15\u201317). Using tf-idf to determine word relevance in document queries. Proceedings of the First Instructional Conference on Machine Learning, Orlando, FL, USA. No. 1."},{"key":"ref_24","unstructured":"Mihalcea, R., and Tarau, P. (2004, January 25\u201326). TextRank: Bringing Order into Text. Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, Barcelona, Spain."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_26","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019, January 2\u20137). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the NAACL-HLT 2019, Minneapolis, MN, USA."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Xue, L., Constant, N., Roberts, A., Kale, M., Al-Rfou, R., Siddhant, A., Barua, A., and Raffel, C. (2021, January 6\u201311). mT5: A Massively Multilingual Pre-Trained Text-to-Text Transformer. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics, Online.","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref_28","first-page":"1","article-title":"UrduBERT: A Bidirectional Transformer for Urdu Language Understanding","volume":"21","author":"Raza","year":"2022","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"ref_29","unstructured":"Sajjad, H., Dalvi, F., Durrani, N., and Nakov, P. (2020, January 5\u201310). Poor Man\u2019s BERT: Smaller and Faster Transformer Models. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hou, L., Hu, P., and Bei, C. (2017, January 8\u201312). Abstractive Document Summarization via Neural Model with Joint Attention. Proceedings of the National CCF Conference on Natural Language Processing and Chinese Computing, Dalian, China.","DOI":"10.1007\/978-3-319-73618-1_28"},{"key":"ref_31","unstructured":"Humayoun, M., Nawab, R., Uzair, M., Aslam, S., and Farzand, O. (2016, January 23\u201328). Urdu Summary Corpus. Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC\u201916), Portoro\u017e, Slovenia."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"61198","DOI":"10.1109\/ACCESS.2024.3378300","article-title":"Abstractive Text Summarization for the Urdu Language: Data and Methods","volume":"12","author":"Awais","year":"2024","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"40311","DOI":"10.1109\/ACCESS.2024.3377463","article-title":"End to End Urdu Abstractive Text Summarization with Dataset and Improvement in Evaluation Metric","volume":"12","author":"Raza","year":"2024","journal-title":"IEEE Access"},{"key":"ref_34","unstructured":"Chen, Q., Zhu, X., Ling, Z., Wei, S., and Jiang, H. (2016). Distraction-Based Neural Networks for Document Summarization. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Gu, J., Lu, Z., Li, H., and Li, V.O. (2016). Incorporating Copying Mechanism in Sequence-to-Sequence Learning. arXiv.","DOI":"10.18653\/v1\/P16-1154"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"102383","DOI":"10.1016\/j.ipm.2020.102383","article-title":"Extractive Text Summarization Models for Urdu Language","volume":"57","author":"Nawaz","year":"2020","journal-title":"Inf. Process. Manag."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Hub, C., and Lcsts, Z. (2015, January 17\u201321). A Large Scale Chinese Short Text Summarization Dataset. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal.","DOI":"10.18653\/v1\/D15-1229"},{"key":"ref_38","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention Is All You Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"113679","DOI":"10.1016\/j.eswa.2020.113679","article-title":"Automatic Text Summarization: A Comprehensive Survey","volume":"165","author":"Salama","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_40","unstructured":"Tan, J., Wan, X., and Xiao, J. (August, January 30). Abstractive Document Summarization with a Graph-Based Attentional Neural Model. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vancouver, Canada."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez, D.Z., Okey, O.D., Maidin, S.S., Udo, E.U., and Kleinschmidt, J.H. (2023). Attentive Transformer Deep Learning Algorithm for Intrusion Detection on IoT Systems Using Automatic Explainable Feature Selection. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0286652"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"e1176","DOI":"10.7717\/peerj-cs.1176","article-title":"Abstractive Text Summarization of Low-Resourced Languages Using Deep Learning","volume":"9","author":"Shafiq","year":"2023","journal-title":"PeerJ Comput. Sci."},{"key":"ref_43","unstructured":"Faheem, A., Ullah, F., Ayub, M.S., and Karim, A. (2024, January 20\u201325). UrduMASD: A Multimodal Abstractive Summarization Dataset for Urdu. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Torino, Italy."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3675780","article-title":"Low Resource Summarization Using Pre-Trained Language Models","volume":"23","author":"Munaf","year":"2024","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"ref_45","unstructured":"Raza, A., Raja, H.S., and Maratib, U. (2023). Abstractive Summary Generation for the Urdu Language. arXiv."},{"key":"ref_46","unstructured":"Raza, A., Soomro, M.H., Shahzad, I., and Batool, S. (2024). Abstractive Text Summarization for Urdu Language. J. Comput. Biomed. Informatics, 7."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"9401","DOI":"10.1007\/s10462-023-10393-8","article-title":"A Review of Semi-Supervised Learning for Text Classification","volume":"56","author":"Duarte","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_48","unstructured":"Bashar, M.A. (2023). A Coherent Knowledge-Driven Deep Learning Model for Idiomatic-Aware Sentiment Analysis of Unstructured Text Using Bert Transformer. [Ph.D. Thesis, Universiti Teknologi MARA]."},{"key":"ref_49","first-page":"200129","article-title":"CORPURES: Benchmark Corpus for Urdu Extractive Summaries and Experiments Using Supervised Learning","volume":"16","author":"Humayoun","year":"2022","journal-title":"Intell. Syst. Appl."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Muhammad, A., Jazeb, N., Martinez-Enriquez, A.M., and Sikander, A. (2018, January 22\u201327). EUTS: Extractive Urdu Text Summarizer. Proceedings of the 2018 Seventeenth Mexican International Conference on Artificial Intelligence (MICAI), Guadalajara, Mexico.","DOI":"10.1109\/MICAI46078.2018.00014"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Saleem, M.A., Shuja, J., Humayun, M.A., Ahmed, S.B., and Ahmad, R.W. (2024). Machine Learning Based Extractive Text Summarization Using Document Aware and Document Unaware Features. Intelligent Systems Modeling and Simulation III: Artificial Intelligence, Machine Learning, Intelligent Functions and Cyber Security, Springer Nature.","DOI":"10.1007\/978-3-031-67317-7_9"},{"key":"ref_52","unstructured":"Syed, M.U., Junaid, M., and Mehmood, I. (2024, October 18). UrduHack: NLP Library for Urdu Language. Available online: https:\/\/urduhack.readthedocs.io\/en\/stable\/reference\/normalization.html."},{"key":"ref_53","unstructured":"Humsha, S. (2024, October 18). Urdu Summarization Corpus (USCorpus). Available online: https:\/\/github.com\/humsha\/USCorpus."},{"key":"ref_54","unstructured":"(2024, October 18). Community Datasets. Urdu Fake News Dataset. Hugging Face, 2022. Available online: https:\/\/huggingface.co\/datasets\/community-datasets\/urdu_fake_news."},{"key":"ref_55","unstructured":"(2024, October 18). mwz. Ursum Dataset. Hugging Face, 2022. Available online: https:\/\/huggingface.co\/datasets\/mwz\/ursum."},{"key":"ref_56","unstructured":"Mustafa, A. (2024, October 18). Urdu Instruct News Article Generation. Hugging Face, 2023. Available online: https:\/\/huggingface.co\/datasets\/AhmadMustafa\/Urdu-Instruct-News-Article-Generation."},{"key":"ref_57","first-page":"1340","article-title":"Exploring Abstractive Text Summarization: Methods, Dataset, Evaluation, and Emerging Challenges","volume":"15","author":"Sunusi","year":"2024","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Barbella, M., and Tortora, G. (2024, October 18). ROUGE Metric Evaluation for Text Summarization Techniques. SSRN 2023. Available online: https:\/\/ssrn.com\/abstract=4120317.","DOI":"10.2139\/ssrn.4120317"},{"key":"ref_59","unstructured":"Paulus, R., Xiong, C., and Socher, R. (2018). A Deep Reinforced Model for Abstractive Summarization. arXiv."},{"key":"ref_60","unstructured":"Smith, L.N. (2018). A Disciplined Approach to Neural Network Hyper-Parameters: Part 1\u2013Learning Rate, Batch Size, Momentum, and Weight Decay. arXiv."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/9\/784\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:42:50Z","timestamp":1760035370000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/9\/784"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,9]]},"references-count":60,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["info16090784"],"URL":"https:\/\/doi.org\/10.3390\/info16090784","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,9]]}}}