{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T11:58:38Z","timestamp":1769169518841,"version":"3.49.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["53C2200043000"],"award-info":[{"award-number":["53C2200043000"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-026-21232-7","type":"journal-article","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T20:25:00Z","timestamp":1769113500000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient translation of HTML to JSON for enhanced web content production"],"prefix":"10.1007","volume":"85","author":[{"given":"Alessandro","family":"Di Stefano","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Massimiliano","family":"Fadda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cinzia","family":"Marini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faisal","family":"Ramzan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8646-6183","authenticated-orcid":false,"given":"Diego","family":"Reforgiato Recupero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,22]]},"reference":[{"key":"21232_CR1","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler D, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. In: Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H (eds) Advances in Neural Information Processing Systems, vol 33, pp 1877\u20131901. Curran Associates, Inc., 7 Morehouse Lane Red Hook, NY 12571 USA. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"21232_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108166","volume":"133","author":"A Cadeddu","year":"2024","unstructured":"Cadeddu A, Chessa A, De Leo V, Fenu G, Motta E, Osborne F, Reforgiato Recupero D, Salatino A, Secchi L (2024) A comparative analysis of knowledge injection strategies for large language models in the scholarly domain. Eng Appl Artif Intell 133:108166. https:\/\/doi.org\/10.1016\/j.engappai.2024.108166","journal-title":"Eng Appl Artif Intell"},{"key":"21232_CR3","doi-asserted-by":"publisher","unstructured":"Buscaldi D, Dess\u00ed D, Motta E, Murgia M, Osborne F, Reforgiato Recupero D (2024) Citation prediction by leveraging transformers and natural language processing heuristics. Inf Process Manag 61(1):103583. https:\/\/doi.org\/10.1016\/j.ipm.2023.103583","DOI":"10.1016\/j.ipm.2023.103583"},{"key":"21232_CR4","doi-asserted-by":"crossref","unstructured":"Tang X, Zong Y, Phang J, Zhao Y, Zhou W, Cohan A, Gerstein M (2023) Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?","DOI":"10.18653\/v1\/2024.naacl-short.2"},{"key":"21232_CR5","doi-asserted-by":"publisher","unstructured":"Gulhane P, Madaan A, Mehta R, Ramamirtham J, Rastogi R, Satpal S, Sengamedu SH, Tengli A, Tiwari C (2011) Web-scale information extraction with vertex. In: 2011 IEEE 27th International conference on data engineering, pp 1209\u20131220. https:\/\/doi.org\/10.1109\/ICDE.2011.5767842","DOI":"10.1109\/ICDE.2011.5767842"},{"key":"21232_CR6","doi-asserted-by":"publisher","unstructured":"Lockard C, Dong XL, Einolghozati A, Shiralkar P (2018) Ceres: distantly supervised relation extraction from the semi-structured web. Proc VLDB Endow 11(10):1084\u20131096. https:\/\/doi.org\/10.14778\/3231751.3231758","DOI":"10.14778\/3231751.3231758"},{"key":"21232_CR7","doi-asserted-by":"publisher","unstructured":"Zhai Y, Liu B (2005) Web data extraction based on partial tree alignment. In: Proceedings of the 14th international conference on world wide web. WWW \u201905, pp 76\u201385. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/1060745.1060761","DOI":"10.1145\/1060745.1060761"},{"key":"21232_CR8","doi-asserted-by":"publisher","unstructured":"Lin BY, Lee D-H, Xu FF, Lan O, Ren X (2019) AlpacaTag: An active learning-based crowd annotation framework for sequence tagging. In: Costa-juss\u00e0 MR, Alfonseca E (eds) Proceedings of the 57th annual meeting of the association for computational linguistics: system demonstrations, pp 58\u201363. Association for Computational Linguistics, Florence, Italy. https:\/\/doi.org\/10.18653\/v1\/P19-3010https:\/\/aclanthology.org\/P19-3010","DOI":"10.18653\/v1\/P19-3010"},{"key":"21232_CR9","doi-asserted-by":"publisher","unstructured":"Hao Q, Cai R, Pang Y, Zhang L (2011) From one tree to a forest: a unified solution for structured web data extraction. In: Proceedings of the 34th International ACM SIGIR conference on research and development in information retrieval. SIGIR \u201911, pp 775\u2013784. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/2009916.2010020","DOI":"10.1145\/2009916.2010020"},{"key":"21232_CR10","doi-asserted-by":"publisher","unstructured":"Omari A, Kimelfeld B, Yahav E, Shoham S (2016) Lossless separation of web pages into layout code and data. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. KDD \u201916, pp 1805\u20131814. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/2939672.2939858","DOI":"10.1145\/2939672.2939858"},{"key":"21232_CR11","doi-asserted-by":"publisher","unstructured":"Lin BY, Sheng Y, Vo N, Tata S (2020) Freedom: A transferable neural architecture for structured information extraction on web documents. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. KDD \u201920, pp 1092\u20131102. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3394486.3403153","DOI":"10.1145\/3394486.3403153"},{"key":"21232_CR12","doi-asserted-by":"publisher","unstructured":"Zhou Y, Sheng Y, Vo N, Edmonds N, Tata S (2022) Learning transferable node representations for attribute extraction from web documents. In: Proceedings of the fifteenth ACM international conference on web search and data mining. WSDM \u201922, pp 1479\u20131487. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3488560.3498424","DOI":"10.1145\/3488560.3498424"},{"key":"21232_CR13","unstructured":"Deng X, Shiralkar P, Lockard C, Huang B, Sun H (2022) DOM-LM: learning generalizable representations for HTML documents. CoRR arXiv:2201.10608"},{"issue":"11","key":"21232_CR14","doi-asserted-by":"publisher","first-page":"13166","DOI":"10.1609\/aaai.v37i11.26546","volume":"37","author":"Z Li","year":"2023","unstructured":"Li Z, Shao B, Shou L, Gong M, Li G, Jiang D (2023) Wiert: Web information extraction via render tree. Proc AAAI Conf Artif Intell 37(11):13166\u201313173. https:\/\/doi.org\/10.1609\/aaai.v37i11.26546","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"21232_CR15","doi-asserted-by":"crossref","unstructured":"Jiang Y, Wang Y, Zeng X, Zhong W, Li L, Mi F, Shang L, Jiang X, Liu Q, Wang W (2023) FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","DOI":"10.18653\/v1\/2024.acl-long.257"},{"key":"21232_CR16","doi-asserted-by":"crossref","unstructured":"Sui Y, Zhou M, Zhou M, Han S, Zhang D (2024) Table meets llm: Can large language models understand structured table data? a benchmark and empirical study. In: The 17th ACM international conference on web search and data mining (WSDM \u201924). https:\/\/www.microsoft.com\/en-us\/research\/publication\/table-meets-llm-can-large-language-models-understand-structured-table-data-a-benchmark-and-empirical-study\/","DOI":"10.1145\/3616855.3635752"},{"key":"21232_CR17","doi-asserted-by":"publisher","unstructured":"Peykani P, Ramezanlou F, Tanasescu C, Ghanidel S (2025) Large language models: A structured taxonomy and review of challenges, limitations, solutions, and future directions. Appl Sci 15(14). https:\/\/doi.org\/10.3390\/app15148103","DOI":"10.3390\/app15148103"},{"key":"21232_CR18","doi-asserted-by":"crossref","unstructured":"Agarwal B, Joshi I, Rojkova V (2025) Think Inside the JSON: Reinforcement Strategy for Strict LLM Schema Adherence. https:\/\/arxiv.org\/abs\/2502.14905","DOI":"10.20944\/preprints202502.1390.v2"},{"key":"21232_CR19","doi-asserted-by":"publisher","unstructured":"Zheng H, Shen L, Tang A, Luo Y, Hu H, Du B, Tao D (2023) Learn from model beyond fine-tuning: A survey. CoRR arXiv:2310.08184https:\/\/doi.org\/10.48550\/ARXIV.2310.08184","DOI":"10.48550\/ARXIV.2310.08184"},{"key":"21232_CR20","doi-asserted-by":"publisher","unstructured":"Willard BT, Louf R (2023) Efficient guided generation for large language models. CoRR arXiv:2307.09702https:\/\/doi.org\/10.48550\/ARXIV.2307.09702","DOI":"10.48550\/ARXIV.2307.09702"},{"key":"21232_CR21","doi-asserted-by":"publisher","unstructured":"Zhan Z, Zhao J, Zhu Z, Tang J (2025) Overcoming Long-Context Limitations of State-Space Models Via Context-Dependent Sparse Attention. https:\/\/doi.org\/10.48550\/arXiv.2507.00449","DOI":"10.48550\/arXiv.2507.00449"},{"key":"21232_CR22","unstructured":"Myung J, Park J, Han J (2025) HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data. https:\/\/arxiv.org\/abs\/2508.18048"},{"key":"21232_CR23","doi-asserted-by":"publisher","unstructured":"Xu Y, Li M, Cui L, Huang S, Wei F, Zhou M (2020) Layoutlm: Pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. KDD \u201920, pp 1192\u20131200. ACM, ???. https:\/\/doi.org\/10.1145\/3394486.3403172http:\/\/dx.doi.org\/10.1145\/3394486.3403172","DOI":"10.1145\/3394486.3403172"},{"key":"21232_CR24","unstructured":"Xu Y, Xu Y, Lv T, Cui L, Wei F, Wang G, Lu Y, Florencio D, Zhang C, Che W, Zhang M, Zhou L (2022) LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding. https:\/\/arxiv.org\/abs\/2012.14740"},{"key":"21232_CR25","doi-asserted-by":"publisher","unstructured":"Gandhewar C, Sawant K, Chafale J, Borkar P, Badhiye S (2024) Doc query: Intelligent document analysis and question answering software. In: 2024 IEEE 6th International conference on cybernetics, cognition and machine learning applications (ICCCMLA), pp 361\u2013364. https:\/\/doi.org\/10.1109\/ICCCMLA63077.2024.10871377","DOI":"10.1109\/ICCCMLA63077.2024.10871377"},{"key":"21232_CR26","unstructured":"Wang F, Shi Z, Wang B, Wang N, Xiao H (2025) ReaderLM-v2: Small Language Model for HTML to Markdown and JSON. https:\/\/arxiv.org\/abs\/2503.01151"},{"key":"21232_CR27","doi-asserted-by":"crossref","unstructured":"Canny JF (1986) A computational approach to edge detection. IEEE. arXiv:2310.08184","DOI":"10.1016\/B978-0-08-051581-6.50024-6"},{"key":"21232_CR28","doi-asserted-by":"publisher","unstructured":"Satoshi\u00a0Suzuki KA (1985) Topological structural analysis of digitized binary images by border following. arXiv:2310.08184https:\/\/doi.org\/10.1016\/0734-189X(85)90016-7","DOI":"10.1016\/0734-189X(85)90016-7"},{"key":"21232_CR29","first-page":"189","volume-title":"Sus: A quick and dirty usability scale","author":"J Brooke","year":"1995","unstructured":"Brooke J (1995) Sus: A quick and dirty usability scale. Usability Eval, Ind, p 189"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21232-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21232-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21232-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T20:25:06Z","timestamp":1769113506000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21232-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,22]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["21232"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21232-7","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,22]]},"assertion":[{"value":"9 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All procedures performed in this study involving human participants were in accordance with institutional and\/or national research committee ethical standards. Ethical approval was not required for this type of study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Participants gave their consent for the results of the study to be published in aggregate form.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Publish"}},{"value":"The authors declare that they have no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"19"}}