{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T14:33:17Z","timestamp":1761921197927,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["POIR.04.02.00-00C002\/19"],"award-info":[{"award-number":["POIR.04.02.00-00C002\/19"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,5]]},"DOI":"10.1145\/3587259.3627548","type":"proceedings-article","created":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T19:30:28Z","timestamp":1701199828000},"page":"105-113","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["PoQuAD - The Polish Question Answering Dataset - Description and Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9610-8048","authenticated-orcid":false,"given":"Ryszard","family":"Tuora","sequence":"first","affiliation":[{"name":"Institute of Computer Science, Polish Academy of Sciences, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7322-7535","authenticated-orcid":false,"given":"Aleksandra","family":"Zwierzchowska","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Polish Academy of Sciences, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4969-2039","authenticated-orcid":false,"given":"Natalia","family":"Zawadzka-Paluektau","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Polish Academy of Sciences, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4321-8862","authenticated-orcid":false,"given":"Cezary","family":"Klamra","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Polish Academy of Sciences, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2462-0020","authenticated-orcid":false,"given":"\u0141ukasz","family":"Kobyli\u0144ski","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Polish Academy of Sciences, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Mohammad\u00a0Yasin Ayoubi Sajjad &\u00a0Davoodeh. 2021. PersianQA: a dataset for Persian Question Answering. https:\/\/github.com\/SajjjadAyobi\/PersianQA."},{"key":"e_1_3_2_1_2_1","unstructured":"Henryk Borzymowski. 2020. Polish QA Model. model trained on HuggingFace https:\/\/huggingface.co\/henryk\/bert-base-multilingual-cased-finetuned-polish-squad2."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Maxime\u00a0De Bruyn Ehsan Lotfi Jeska Buhmann and Walter Daelemans. 2021. MFAQ: a Multilingual FAQ Dataset. arxiv:2109.12870\u00a0[cs.CL]","DOI":"10.18653\/v1\/2021.mrqa-1.1"},{"key":"e_1_3_2_1_4_1","volume-title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model. arXiv preprint arXiv:2205.08808","author":"Chrabrowa Aleksandra","year":"2022","unstructured":"Aleksandra Chrabrowa, \u0141ukasz Dragan, Karol Grzegorczyk, Dariusz Kajtoch, Miko\u0142aj Koszowski, Robert Mroczkowski, and Piotr Rybak. 2022. Evaluation of Transfer Learning for Polish with a Text-to-Text Model. arXiv preprint arXiv:2205.08808 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Unsupervised Cross-lingual Representation Learning at Scale. CoRR","author":"Conneau Alexis","year":"2019","unstructured":"Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzm\u00e1n, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Unsupervised Cross-lingual Representation Learning at Scale. CoRR (2019). arXiv:1911.02116http:\/\/arxiv.org\/abs\/1911.02116"},{"key":"e_1_3_2_1_6_1","unstructured":"S\u0142awomir Dadas. [n. d.]. Polish BART. https:\/\/github.com\/sdadas\/polish-nlp-resources#bart"},{"key":"e_1_3_2_1_7_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR (2018). arxiv:1810.04805http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Martin d\u2019Hoffschmidt Wacim Belblidia Tom Brendl\u00e9 Quentin Heinrich and Maxime Vidal. 2020. FQuAD: French Question Answering Dataset. https:\/\/doi.org\/10.48550\/ARXIV.2002.06071","DOI":"10.48550\/ARXIV.2002.06071"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58219-7_1"},{"key":"e_1_3_2_1_10_1","volume-title":"Know. In Proceedings of the Thirteenth Language Resources and Evaluation Conference. European Language Resources Association","author":"Heinrich Quentin","year":"2022","unstructured":"Quentin Heinrich, Gautier Viaud, and Wacim Belblidia. 2022. FQuAD2.0: French Question Answering and Learning When You Don\u2019t Know. In Proceedings of the Thirteenth Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 2205\u20132214. https:\/\/aclanthology.org\/2022.lrec-1.237"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3262308"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Robin Jia and Percy Liang. 2017. Adversarial Examples for Evaluating Reading Comprehension Systems. arxiv:1707.07328\u00a0[cs.CL]","DOI":"10.18653\/v1\/D17-1215"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Seungyoung Lim Myungji Kim and Jooyoul Lee. 2019. KorQuAD1.0: Korean QA Dataset for Machine Reading Comprehension. https:\/\/doi.org\/10.48550\/ARXIV.1909.07005","DOI":"10.48550\/ARXIV.1909.07005"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1227"},{"key":"e_1_3_2_1_15_1","volume-title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering. https:\/\/arxiv.org\/pdf\/2007.15207.pdf","author":"Longpre Shayne","year":"2020","unstructured":"Shayne Longpre, Yi Lu, and Joachim Daiber. 2020. MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering. https:\/\/arxiv.org\/pdf\/2007.15207.pdf"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Kate\u0159ina Mackov\u00e1 and Milan Straka. 2020. Reading Comprehension in Czech via Machine Translation and Cross-lingual Transfer. https:\/\/doi.org\/10.48550\/ARXIV.2007.01667","DOI":"10.48550\/ARXIV.2007.01667"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the International Conference Recent Advances in Natural Language Processing RANLP","author":"Marci\u0144czuk Micha\u0142","year":"2013","unstructured":"Micha\u0142 Marci\u0144czuk, Adam Radziszewski, Maciej Piasecki, Dominik Piasecki, and Marcin Ptak. 2013. Evaluation of baseline information retrieval for Polish open-domain Question Answering system. In Proceedings of the International Conference Recent Advances in Natural Language Processing RANLP 2013. INCOMA Ltd. Shoumen, BULGARIA, Hissar, Bulgaria, 428\u2013435. https:\/\/aclanthology.org\/R13-1056"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing. Association for Computational Linguistics","author":"Mroczkowski Robert","year":"2021","unstructured":"Robert Mroczkowski, Piotr Rybak, Alina Wr\u00f3blewska, and Ireneusz Gawlik. 2021. HerBERT: Efficiently Pretrained Transformer-based Language Model for Polish. In Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing. Association for Computational Linguistics, Kiyv, Ukraine, 1\u201310. https:\/\/www.aclweb.org\/anthology\/2021.bsnlp-1.1"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Timo M\u00f6ller Julian Risch and Malte Pietsch. 2021. GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval. https:\/\/doi.org\/10.48550\/ARXIV.2104.12741","DOI":"10.48550\/ARXIV.2104.12741"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.233"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Pranav Rajpurkar Robin Jia and Percy Liang. 2018. Know What You Don\u2019t Know: Unanswerable Questions for SQuAD. https:\/\/doi.org\/10.48550\/ARXIV.1806.03822","DOI":"10.48550\/ARXIV.1806.03822"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560260"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.bsnlp-1.2"},{"key":"e_1_3_2_1_25_1","unstructured":"Piotr Rybak Piotr Przyby\u0142a and Maciej Ogrodniczuk. 2022. Improving Question Answering Performance through Manual Annotation: Costs Benefits and Strategies. arxiv:2212.08897\u00a0[cs.CL]"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the Thirteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2019 (Brno), Ale\u0161 Hor\u00e1k, Pavel Rychl\u00fd, and Adam Rambousek (Eds.). Tribun EU, Brno, 99\u2013108","author":"Sabol Radoslav","year":"2019","unstructured":"Radoslav Sabol, Marek Medve\u010f, and Ale\u0161 Hor\u00e1k. 2019. Czech Question Answering with Extended SQAD v3.0 Benchmark Dataset. ti\u0161t\u011bn\u00e1 verze \"print\". In Proceedings of the Thirteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2019 (Brno), Ale\u0161 Hor\u00e1k, Pavel Rychl\u00fd, and Adam Rambousek (Eds.). Tribun EU, Brno, 99\u2013108."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association","author":"Schlegel Viktor","year":"2020","unstructured":"Viktor Schlegel, Marco Valentino, Andre Freitas, Goran Nenadic, and Riza Batista-Navarro. 2020. A Framework for Evaluation of Machine Reading Comprehension Gold Standards. In Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 5359\u20135369. https:\/\/aclanthology.org\/2020.lrec-1.660"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.190"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"ByungHoon So Kyuhong Byun Kyungwon Kang and Seongjin Cho. 2022. JaQuAD: Japanese Question Answering Dataset for Machine Reading Comprehension. https:\/\/doi.org\/10.48550\/ARXIV.2202.01764","DOI":"10.48550\/ARXIV.2202.01764"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Saku Sugawara Kentaro Inui Satoshi Sekine and Akiko Aizawa. 2018. What Makes Reading Comprehension Questions Easier?arxiv:1808.09384\u00a0[cs.CL]","DOI":"10.18653\/v1\/D18-1453"},{"key":"e_1_3_2_1_31_1","volume-title":"mT5: A massively multilingual pre-trained text-to-text transformer. CoRR","author":"Xue Linting","year":"2020","unstructured":"Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2020. mT5: A massively multilingual pre-trained text-to-text transformer. CoRR (2020). arXiv:2010.11934https:\/\/arxiv.org\/abs\/2010.11934"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1241"},{"key":"e_1_3_2_1_33_1","unstructured":"Changchang Zeng Shaobo Li Qin Li Jie Hu and Jianjun Hu. 2020. A Survey on Machine Reading Comprehension: Tasks Evaluation Metrics and Benchmark Datasets. arxiv:2006.11880\u00a0[cs.CL]"}],"event":{"name":"K-CAP '23: Knowledge Capture Conference 2023","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"],"location":"Pensacola FL USA","acronym":"K-CAP '23"},"container-title":["Proceedings of the 12th Knowledge Capture Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3587259.3627548","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3587259.3627548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T23:44:27Z","timestamp":1755906267000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3587259.3627548"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":33,"alternative-id":["10.1145\/3587259.3627548","10.1145\/3587259"],"URL":"https:\/\/doi.org\/10.1145\/3587259.3627548","relation":{},"subject":[],"published":{"date-parts":[[2023,12,5]]},"assertion":[{"value":"2023-12-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}