{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:46:05Z","timestamp":1778010365139,"version":"3.51.4"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006109","name":"Deutsche Telekom IT & Telecommunications Slovakia by the Scientific Grant Agency of the Ministry of Education, Science, Research and Sport of the Slovak Republic and the Slovak Academy of Sciences","doi-asserted-by":"publisher","award":["VEGA 2\/0165\/21"],"award-info":[{"award-number":["VEGA 2\/0165\/21"]}],"id":[{"id":"10.13039\/501100006109","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006108","name":"Cultural and Educational Grant Agency of the Slovak Republic","doi-asserted-by":"publisher","award":["KEGA 055TUKE-4\/2023"],"award-info":[{"award-number":["KEGA 055TUKE-4\/2023"]}],"id":[{"id":"10.13039\/501100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005357","name":"Ministry of Education, Science, Research and Sport of the Slovak Republic and the Slovak Research and Development Agency through the Project of Bilateral Cooperation","doi-asserted-by":"publisher","award":["APVV-SK-TW-21-0002"],"award-info":[{"award-number":["APVV-SK-TW-21-0002"]}],"id":[{"id":"10.13039\/501100005357","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3262308","type":"journal-article","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T18:54:52Z","timestamp":1679943292000},"page":"32869-32881","source":"Crossref","is-referenced-by-count":11,"title":["Slovak Dataset for Multilingual Question Answering"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1148-3194","authenticated-orcid":false,"given":"Daniel","family":"Hl\u00e1dek","sequence":"first","affiliation":[{"name":"Faculty of Electrical Engineering and Informatics, Technical University of Košice, Košice, Slovakia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7403-0235","authenticated-orcid":false,"given":"J\u00e1n","family":"Sta\u0161","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Informatics, Technical University of Košice, Košice, Slovakia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-9258","authenticated-orcid":false,"given":"Jozef","family":"Juh\u00e1r","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Informatics, Technical University of Košice, Košice, Slovakia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom\u00e1\u0161","family":"Koct\u00far","sequence":"additional","affiliation":[{"name":"Deutsche Telekom IT & Telecommunications Slovakia, Košice, Slovakia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"ref2","volume-title":"Neural Reading Comprehension and Beyond","author":"Chen","year":"2018"},{"issue":"21","key":"ref3","doi-asserted-by":"crossref","first-page":"7640","DOI":"10.3390\/app10217640","article-title":"A survey on machine reading comprehension\u2014Tasks, evaluation metrics and benchmark datasets","volume":"10","author":"Zeng","year":"2020","journal-title":"Appl. Sci."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-022-09577-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"issue":"18","key":"ref8","doi-asserted-by":"crossref","first-page":"3698","DOI":"10.3390\/app9183698","article-title":"Neural machine reading comprehension: Methods and trends","volume":"9","author":"Liu","year":"2019","journal-title":"Appl. Sci."},{"key":"ref9","article-title":"Machine reading comprehension: A literature review","author":"Zhang","year":"2019","journal-title":"arXiv:1907.01686"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3483382.3483389"},{"key":"ref11","first-page":"8784","article-title":"English machine reading comprehension datasets: A survey","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP)","author":"Dzendzik"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/24751839.2020.1833136"},{"key":"ref13","article-title":"Question answering survey: Directions, challenges, datasets, evaluation matrices","author":"Pandya","year":"2021","journal-title":"arXiv:2112.03572"},{"key":"ref14","article-title":"Retrieving and reading: A comprehensive survey on open-domain question answering","author":"Zhu","year":"2021","journal-title":"arXiv:2101.00774"},{"key":"ref15","article-title":"More than reading comprehension: A survey on datasets and metrics of textual question answering","author":"Bai","year":"2021","journal-title":"arXiv:2109.12264"},{"key":"ref16","article-title":"A survey on machine reading comprehension systems","author":"Baradaran","year":"2020","journal-title":"arXiv:2001.01582"},{"key":"ref17","article-title":"Modern question answering datasets and benchmarks: A survey","author":"Wang","year":"2022","journal-title":"arXiv:2206.15030"},{"key":"ref18","first-page":"2383","article-title":"Squad: 100,000+ questions for machine comprehension of text","volume-title":"Proc. EMNLP","author":"Rajpurkar"},{"key":"ref19","article-title":"A survey on non-English question answering dataset","author":"Chandra","year":"2021","journal-title":"arXiv:2112.13634"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3560260"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03840-3_29"},{"key":"ref22","first-page":"5515","article-title":"Automatic Spanish translation of SQuAD dataset for multi-lingual question answering","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Carrino"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58323-1_18"},{"key":"ref24","first-page":"1","article-title":"Semi-supervised training data generation for multilingual question answering","volume-title":"Proc. 11th Int. Conf. Lang. Resour. Eval. (LREC)","author":"Lee"},{"key":"ref25","first-page":"81","article-title":"Context-based question-answering system for the Ukrainian language","volume-title":"Proc. 1st Masters Symp. Adv. Data Mining, Mach. Learn., Comput. Vis. (MS-AMLV)","author":"Tiutiunnyk"},{"key":"ref26","volume-title":"SQuAD-PL\u2014Polish Google Translated SQuAD v2.0 Dataset","author":"Brodzik","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4612"},{"key":"ref28","first-page":"244","article-title":"On the usability of transformers-based models for a French question-answering task","volume-title":"Proc. Int. Conf. Recent Adv. Natural Lang. Process. (RANLP)","author":"Cattan"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3359988"},{"issue":"1","key":"ref30","first-page":"34","article-title":"ParSQuAD: Persian question answering dataset based on machine translation of SQuAD 2.0","volume":"4","author":"Abadani","year":"2021","journal-title":"Int. J. Web Res."},{"key":"ref31","volume-title":"PolAQ\u2014Polish Answers and Questions","author":"Jurkiewicz","year":"2020"},{"key":"ref32","volume-title":"Question-Answering Model Fine-Tuned for Portuguese","author":"Carvalho","year":"2019"},{"key":"ref33","volume-title":"Portuguese Translation of SQuAD 2.0 Dataset","author":"Janiake","year":"2020"},{"key":"ref34","volume-title":"Swedish Version of SQuAD 2.0","author":"Okazawa","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.107"},{"key":"ref36","first-page":"2205","article-title":"FQuAD2.0: French question answering and learning when you don\u2019t know","volume-title":"Proc. 13th Lang. Resour. Eval. Conf.","author":"Heinrich"},{"key":"ref37","article-title":"KorQuAD1.0: Korean QA dataset for machine reading comprehension","author":"Lim","year":"2019","journal-title":"arXiv:1909.07005"},{"issue":"6","key":"ref38","doi-asserted-by":"crossref","first-page":"577","DOI":"10.5626\/JOK.2020.47.6.577","article-title":"KorQuAD 2.0: Korean QA dataset for web document machine comprehension","volume":"47","author":"Kim","year":"2020","journal-title":"J. KIISE"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58219-7_1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-056-4_053"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2019.00084"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/UBMK52708.2021.9559013"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3578553"},{"key":"ref44","first-page":"99","article-title":"Czech question answering with extended SQAD v3.0 benchmark dataset","volume-title":"Proc. 13th Workshop Recent Adv. Slavonic Natural Lang. Process.","author":"Sabol"},{"key":"ref45","first-page":"5481","article-title":"Project PIAF: Building a native French question-answering dataset","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Keraron"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3157289"},{"key":"ref47","first-page":"106","article-title":"ParaShoot: A Hebrew question answering dataset","volume-title":"Proc. 3rd Workshop Mach. Reading Question Answering","author":"Keren"},{"key":"ref48","volume-title":"ViquiQuAD: An Extractive QA Dataset From Catalan Wikipedia","author":"Rodriguez-Penagos","year":"2021"},{"key":"ref49","volume-title":"VilaQuAD: An Extractive QA Dataset From Catalan Newswire","author":"Rodriguez-Penagos","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.mrqa-1.4"},{"key":"ref51","article-title":"DRCD: A Chinese machine reading comprehension dataset","author":"Shao","year":"2018","journal-title":"arXiv:1806.00920"},{"key":"ref52","first-page":"5883","article-title":"A span-extraction dataset for Chinese machine reading comprehension","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process. (EMNLP-IJCNLP)","author":"Cui"},{"key":"ref53","article-title":"Automated methods for question-answering in Icelandic","author":"Sn\u00e6bjarnarson","year":"2021"},{"key":"ref54","article-title":"JaQuAD: Japanese question answering dataset for machine reading comprehension","author":"So","year":"2022","journal-title":"arXiv:2202.01764"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2023.101486"},{"key":"ref56","article-title":"MarIA: Spanish language models","author":"Guti\u00e9rrez-Fandi no","year":"2021","journal-title":"arXiv:2107.07253"},{"key":"ref57","volume-title":"Question Answering Model in Thai by Using SQuAD Thai Wikipedia Dataset","author":"Rueangkhajorn","year":"2021"},{"key":"ref58","volume-title":"Dataset Card for Thaiqa-Squad","author":"Suriyawongkul","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.233"},{"key":"ref60","volume-title":"UA_Datasets: A Collection of Ukrainian Language Datasets","author":"Ivanyuk-Skulskiy","year":"2021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10796-020-09996-1"},{"key":"ref62","first-page":"2358","article-title":"XQA: A cross-lingual open-domain question answering dataset","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Liu"},{"key":"ref63","first-page":"4623","article-title":"On the cross-lingual transferability of monolingual representations","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Artetxe"},{"key":"ref64","first-page":"7315","article-title":"MLQA: Evaluating cross-lingual extractive question answering","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Lewis"},{"key":"ref65","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1162\/tacl_a_00317","article-title":"TyDi QA: A benchmark for information-seeking question answering in typologically diverse languages","volume":"8","author":"Clark","year":"2020","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"ref66","first-page":"547","article-title":"XOR QA: Cross-lingual open-retrieval question answering","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Asai"},{"key":"ref67","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1162\/tacl_a_00433","article-title":"MKQA: A linguistically diverse benchmark for multilingual open domain question answering","volume":"9","author":"Longpre","year":"2021","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"ref68","first-page":"452","article-title":"Natural questions: A benchmark for question answering research","volume":"7","author":"Kwiatkowski","year":"2019","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"ref69","first-page":"1","article-title":"Generating sets of synonyms between languages","volume-title":"Proc. 6th Int. Conf. Natural Lang. Process., Multilinguality","author":"Dzurjuv"},{"issue":"2","key":"ref70","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1515\/jazcas-2017-0048","article-title":"Slovak dependency treebank in universal dependencies","volume":"68","author":"Zeman","year":"2017","journal-title":"J. Linguistics\/Jazykovedn\u00fd Casopis"},{"key":"ref71","first-page":"4245","article-title":"Two years of Aranea: Increasing counts and tuning the pipeline","volume-title":"Proc. 10th Int. Conf. Lang. Resour. Eval. (LREC)","author":"Benko"},{"key":"ref72","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref73","doi-asserted-by":"crossref","first-page":"7156","DOI":"10.18653\/v1\/2022.findings-emnlp.530","article-title":"SlovakBERT: Slovak masked language model","volume-title":"Findings of the Association for Computational Linguistics: EMNLP","author":"Pikuliak","year":"2022"},{"key":"ref74","first-page":"1913","article-title":"Evaluation set for Slovak news information retrieval","volume-title":"Proc. 10th Int. Conf. Lang. Resour. Eval. (LREC)","author":"Hl\u00e1dek"},{"key":"ref75","volume-title":"Prodigy\u2014Radically Efficient Machine Teaching. An Annotation Tool Powered by Active Learning","year":"2022"},{"key":"ref76","volume-title":"Hunspell-Sk\u2014Slovak Dictionary for HunSpell","year":"2022"},{"key":"ref77","first-page":"116","article-title":"Marian: Fast neural machine translation in C++","volume-title":"Proc. ACL Syst. Demonstrations","author":"Junczys-Dowmunt"},{"key":"ref78","first-page":"479","article-title":"OPUS-MT\u2014Building open translation services for the World","volume-title":"Proc. 22nd Annu. Conf. Eur. Assoc. Mach. Transl.","author":"Tiedemann"},{"key":"ref79","article-title":"spaCy: Industrial-strength natural language processing in Python","author":"Honnibal","year":"2020"},{"key":"ref80","doi-asserted-by":"crossref","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. Linguistics"},{"key":"ref81","volume-title":"Floret: FastText + Bloom Embeddings for Compact, Full-Coverage Vectors With spaCy","year":"2022"},{"issue":"1","key":"ref82","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/1687-4722-2014-14","article-title":"Classification of heterogeneous text data for robust domain-specific language modeling","volume":"2014","author":"Sta\u0161","year":"2014","journal-title":"EURASIP J. Audio, Speech, Music Process."},{"issue":"1","key":"ref83","first-page":"65","article-title":"Text mining and processing for corpora creation in Slovak language","volume":"3","author":"Hl\u00e1dek","year":"2010","journal-title":"J. Comput. Sci. Control Syst."},{"key":"ref84","volume-title":"Slovak spaCy Model","author":"Hl\u00e1dek","year":"2022"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3207569"},{"key":"ref86","first-page":"120","article-title":"Are all languages created equal in multilingual BERT?","volume-title":"Proc. 5th Workshop Represent. Learn. NLP","author":"Wu"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10082887.pdf?arnumber=10082887","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T16:46:25Z","timestamp":1707842785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10082887\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3262308","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}