{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T12:05:12Z","timestamp":1791893112906,"version":"4.3.4"},"reference-count":19,"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":[[2026,7,29]],"date-time":"2026-07-29T00:00:00Z","timestamp":1785283200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/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.2026.113129","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T16:05:09Z","timestamp":1785773109000},"page":"113129","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Dasinya: A dataset and preprocessing pipeline for the Badini Kurdish dialect"],"prefix":"10.1016","volume":"68","author":[{"given":"Vaman A.","family":"Saeed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5220-5548","authenticated-orcid":false,"given":"Karwan","family":"Jacksi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.dib.2026.113129_bib0001","series-title":"KLPT \u2014 Kurdish language processing toolkit","first-page":"72","author":"Ahmadi","year":"2020"},{"issue":"4","key":"10.1016\/j.dib.2026.113129_bib0002","doi-asserted-by":"crossref","first-page":"1604","DOI":"10.1093\/llc\/fqad066","article-title":"A hybrid part-of-speech tagger with annotated Kurdish corpus: advancements in POS tagging","volume":"38","author":"Maulud","year":"2023","journal-title":"Digit. Scholarsh. Humanit."},{"key":"10.1016\/j.dib.2026.113129_bib0003","doi-asserted-by":"crossref","first-page":"15","DOI":"10.53898\/josse2025531","article-title":"A comprehensive part-of-speech tagging to standardize Central-Kurdish language: a research guide for Kurdish NLP tasks","volume":"5","author":"Sabr","year":"2025","journal-title":"J. Stud. Sci. Eng."},{"key":"10.1016\/j.dib.2026.113129_bib0004","series-title":"2013 ACS International Conference on Computer Systems and Applications (AICCSA)","first-page":"1","article-title":"Building a test collection for Sorani Kurdish","author":"Sheykh Esmaili","year":"2013"},{"issue":"2","key":"10.1016\/j.dib.2026.113129_bib0005","first-page":"7","article-title":"Towards Kurdish information retrieval","volume":"13","author":"Esmaili","year":"2014","journal-title":"ACM Transac. Asian Lang. Infor. Proc."},{"issue":"1","key":"10.1016\/j.dib.2026.113129_bib0006","first-page":"176","article-title":"Toward kurdish language processing: experiments in collecting and processing the AsoSoft text corpus","volume":"35","author":"Veisi","year":"2020","journal-title":"Digit. Scholarsh. Humanit."},{"issue":"10","key":"10.1016\/j.dib.2026.113129_bib0007","doi-asserted-by":"crossref","first-page":"578","DOI":"10.3390\/info15090578","article-title":"A hybrid approach to ontology construction for the Badini Kurdish language","volume":"15","author":"Azzat","year":"2024","journal-title":"Information"},{"key":"10.1016\/j.dib.2026.113129_bib0008","article-title":"KurCorpus 2B: A multidialectal 2-billion-token corpus for Kurdish language modeling [Data set]","volume":"V1","author":"Rawf","year":"2025","journal-title":"Mendeley Data"},{"key":"10.1016\/j.dib.2026.113129_bib0009","article-title":"KSTRV1: a scene text recognition dataset for central Kurdish in (Arabic-Based) script","volume":"60","author":"Salih","year":"2025","journal-title":"Data Br."},{"key":"10.1016\/j.dib.2026.113129_bib0010","article-title":"Adyan: automated annotating named entity recognition dataset for Sorani Kurdish language","volume":"62","author":"Wahid","year":"2025","journal-title":"Data Br."},{"key":"10.1016\/j.dib.2026.113129_bib0011","article-title":"Bochun: automatically annotated stance detection dataset for Sorani Kurdish language","volume":"61","author":"Rostam","year":"2025","journal-title":"Data Br."},{"key":"10.1016\/j.dib.2026.113129_bib0012","unstructured":"Abas, A., Veisi, H., Ali, H.M. (2025). KurdSTS: The Kurdish semantic textual similarity [Preprint]. arXiv. doi:10.48550\/arXiv.2510.02336."},{"key":"10.1016\/j.dib.2026.113129_bib0013","unstructured":"Abdalla, B., Nabi, R.M., Eshkiki, H., Caraffini, F. (2025). Named entity recognition for the Kurdish Sorani language: Dataset creation and comparative analysis [Preprint]. arXiv. doi:10.48550\/arXiv.2511.22315."},{"key":"10.1016\/j.dib.2026.113129_bib0014","author":"Jaff"},{"key":"10.1016\/j.dib.2026.113129_bib0015","unstructured":"Bedirxan, C.A. (2021). Elfab\u00eaya kurd\u00ee \u00fb bingeh\u00ean gram\u00eara kurdmanc\u00ee (M. X. Guli, Trans.; A. Z\u00earevan, Ed.). Nalbend, Duhok. (Original work published 1932\u20131943)."},{"key":"10.1016\/j.dib.2026.113129_bib0016","series-title":"Ferhenga rastniv\u00eesa ziman\u00ea Kurd\u00ee [Kurdish orthographic dictionary]","author":"Abdullah","year":"2021"},{"key":"10.1016\/j.dib.2026.113129_bib0017","unstructured":"Kaval, M. (2022). Hevok d ziman\u00ea kurd\u00ee da [Sentences in Kurdish] (M. X. Gul\u00ee, Trans.). Xan\u00ee Cultural and Media Centre, Duhok, Kurdistan Region, Iraq."},{"key":"10.1016\/j.dib.2026.113129_bib0018","unstructured":"Read, J., Dridan, R., Oepen, S., Solberg, L.J. (2012). Sentence boundary detection: A long solved problem? In Proceedings of COLING 2012: Posters (pp. 985\u2013994). Mumbai, India: The COLING 2012 Organizing Committee. https:\/\/aclanthology.org\/C12-2096."},{"key":"10.1016\/j.dib.2026.113129_bib0019","author":"Saeed","year":"2026","journal-title":"Dasinya \u2014 Badini Kurdish corpus and BDPT pipeline [Data set]. Zenodo"}],"container-title":["Data in Brief"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352340926006761?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352340926006761?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T11:43:40Z","timestamp":1791891820000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2352340926006761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":19,"alternative-id":["S2352340926006761"],"URL":"https:\/\/doi.org\/10.1016\/j.dib.2026.113129","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":"Dasinya: A dataset and preprocessing pipeline for the Badini Kurdish dialect","name":"articletitle","label":"Article Title"},{"value":"Data in Brief","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dib.2026.113129","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":"113129"}}