{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T17:27:45Z","timestamp":1793640465382,"version":"4.5.1"},"reference-count":20,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"vor","delay-in-days":45,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Data in Brief"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.dib.2026.113275","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T15:34:17Z","timestamp":1789745657000},"page":"113275","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A multilingual annotated dataset for metadata extraction from Persian, Arabic and English scientific articles: header and reference section annotations"],"prefix":"10.1016","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8136-2246","authenticated-orcid":false,"given":"Arash","family":"Yousefi Jordehi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reza","family":"Fallah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ebrahim","family":"Nikmard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5295-2789","authenticated-orcid":false,"given":"Mahsa","family":"Hosseini Khasheh Heyran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8853-9112","authenticated-orcid":false,"given":"Seyed Abolghasem","family":"Mirroshandel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.dib.2026.113275_bib0001","article-title":"A multilingual annotated dataset for metadata extraction from Persian, Arabic and English scientific articles","volume":"V1","author":"Yousefi Jordehi","year":"2026","journal-title":"Mendeley Data"},{"key":"10.1016\/j.dib.2026.113275_bib0002","series-title":"International Conference on Theory and Practice of Digital Libraries","first-page":"473","article-title":"GROBID: combining automatic bibliographic data recognition and term extraction for scholarship publications","author":"Lopez","year":"2009"},{"key":"10.1016\/j.dib.2026.113275_bib0003","series-title":"Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC)","doi-asserted-by":"crossref","first-page":"661","DOI":"10.63317\/3pp9nrrhs7x9","article-title":"ParsCit: an open-source CRF reference string parsing package","author":"Councill","year":"2008"},{"key":"10.1016\/j.dib.2026.113275_bib0004","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/s10032-015-0249-8","article-title":"CERMINE: automatic extraction of structured metadata from scientific literature","volume":"18","author":"Tkaczyk","year":"2015","journal-title":"Int. J. Doc. Anal. Recognit. (IJDAR)"},{"key":"10.1016\/j.dib.2026.113275_bib0005","series-title":"Proceedings of the 8th ACM\/IEEE-CS Joint Conference on Digital Libraries","first-page":"423","article-title":"A simple method for citation metadata extraction using hidden Markov models","author":"Hetzner","year":"2008"},{"key":"10.1016\/j.dib.2026.113275_bib0006","series-title":"International Conference on Asian Digital Libraries","first-page":"338","article-title":"Metadata extraction from bibliographies using bigram HMM","author":"Yin","year":"2004"},{"issue":"9","key":"10.1016\/j.dib.2026.113275_bib0007","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1016\/j.ins.2011.01.014","article-title":"A trigram hidden Markov model for metadata extraction from heterogeneous references","volume":"181","author":"Ojokoh","year":"2011","journal-title":"Inf. Sci."},{"key":"10.1016\/j.dib.2026.113275_bib0008","series-title":"2016 Eleventh International Conference on Digital Information Management (ICDIM)","article-title":"Examination of effective features for CRF-based bibliography extraction from reference strings","author":"Matsuoka","year":"2016"},{"issue":"4","key":"10.1016\/j.dib.2026.113275_bib0009","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.compbiomed.2011.02.005","article-title":"Parsing citations in biomedical articles using conditional random fields","volume":"41","author":"Zhang","year":"2011","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.dib.2026.113275_bib0010","series-title":"2010 Ninth International Conference on Machine Learning and Applications","article-title":"A structural SVM approach for reference parsing","author":"Zhang","year":"2010"},{"issue":"2","key":"10.1016\/j.dib.2026.113275_bib0011","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1109\/TKDE.2010.231","article-title":"BibPro: a citation parser based on sequence alignment","volume":"24","author":"Chen","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"1","key":"10.1016\/j.dib.2026.113275_bib0012","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.dss.2006.08.006","article-title":"Reference metadata extraction using a hierarchical knowledge representation framework","volume":"43","author":"Day","year":"2007","journal-title":"Decis. Support. Syst."},{"key":"10.1016\/j.dib.2026.113275_bib0013","series-title":"2011 12th International Conference on Parallel and Distributed Computing, Applications and Technologies","article-title":"Reference metadata extraction from scientific papers","author":"Guo","year":"2011"},{"key":"10.1016\/j.dib.2026.113275_bib0014","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s10032-009-0105-9","article-title":"Locating and parsing bibliographic references in HTML medical articles","volume":"13","author":"Zou","year":"2010","journal-title":"Int. J. Doc. Anal. Recognit. (IJDAR)"},{"key":"10.1016\/j.dib.2026.113275_bib0015","unstructured":"D. Tkaczyk, New methods for metadata extraction from scientific literature, arXiv preprint arXiv:1710.10201, 2017."},{"key":"10.1016\/j.dib.2026.113275_bib0016","series-title":"Proceedings of the 18th ACM\/IEEE Joint Conference on Digital Libraries","first-page":"103","article-title":"Machine learning vs. rules and out-of-the-box vs. retrained: an evaluation of open-source bibliographic reference and citation parsers","author":"Tkaczyk","year":"2018"},{"key":"10.1016\/j.dib.2026.113275_bib0017","unstructured":"D. Tkaczyk, R. Gupta, R. Cinti, J. Beel, ParsRec: a novel meta-learning approach to recommending bibliographic reference parsers, arXiv preprint arXiv:1811.10369, 2018."},{"key":"10.1016\/j.dib.2026.113275_bib0018","unstructured":"Apache Software Foundation, Apache Tika: content analysis toolkit, https:\/\/tika.apache.org\/ (accessed 26 August 2026)."},{"key":"10.1016\/j.dib.2026.113275_bib0019","unstructured":"Apache Software Foundation, PDFBox: Java PDF library, https:\/\/pdfbox.apache.org\/ (accessed 26 August 2026)."},{"issue":"1","key":"10.1016\/j.dib.2026.113275_bib0020","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"Landis","year":"1977","journal-title":"Biometrics"}],"container-title":["Data in Brief"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S235234092600822X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S235234092600822X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T16:50:27Z","timestamp":1793638227000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S235234092600822X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":20,"alternative-id":["S235234092600822X"],"URL":"https:\/\/doi.org\/10.1016\/j.dib.2026.113275","relation":{},"ISSN":["2352-3409"],"issn-type":[{"value":"2352-3409","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A multilingual annotated dataset for metadata extraction from Persian, Arabic and English scientific articles: header and reference section annotations","name":"articletitle","label":"Article Title"},{"value":"Data in Brief","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dib.2026.113275","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"113275"}}