{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:38:07Z","timestamp":1771699087916,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031843525","type":"print"},{"value":"9783031843532","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-84353-2_4","type":"book-chapter","created":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T13:49:39Z","timestamp":1740491379000},"page":"37-49","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Assessing Generalization Capability of\u00a0Text Ranking Models in\u00a0Polish"],"prefix":"10.1007","author":[{"given":"S\u0142awomir","family":"Dadas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ma\u0142gorzata","family":"Gr\u0229bowiec","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,17]]},"reference":[{"key":"4_CR1","unstructured":"Bajaj, P., et\u00a0al.: MS MARCO: a human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)"},{"key":"4_CR2","unstructured":"Bonifacio, et al.: mMARCO: a multilingual version of MS MARCO passage ranking dataset (2021)"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Burges, C., et al.: Learning to rank using gradient descent. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 89\u201396 (2005)","DOI":"10.1145\/1102351.1102363"},{"key":"4_CR4","unstructured":"Chrabrowa, A., et al.: Evaluation of transfer learning for Polish with a text-to-text model. In: Calzolari, N., et al. (eds.) Proceedings of the Thirteenth Language Resources and Evaluation Conference. pp. 4374\u20134394. European Language Resources Association, Marseille, France, June 2022. https:\/\/aclanthology.org\/2022.lrec-1.466"},{"key":"4_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1007\/978-3-030-61534-5_27","volume-title":"Artificial Intelligence and Soft Computing","author":"S Dadas","year":"2020","unstructured":"Dadas, S., Pere\u0142kiewicz, M., Po\u015bwiata, R.: Pre-training polish transformer-based language models at scale. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2020. LNCS (LNAI), vol. 12416, pp. 301\u2013314. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61534-5_27"},{"key":"4_CR6","unstructured":"Dadas, S., Pere\u0142kiewicz, M., Po\u015bwiata, R.: PIRB: a comprehensive benchmark of polish dense and hybrid text retrieval methods (2024)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Formal, T., Lassance, C., Piwowarski, B., Clinchant, S.: From distillation to hard negative sampling: making sparse neural IR models more effective. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2353\u20132359 (2022)","DOI":"10.1145\/3477495.3531857"},{"issue":"6","key":"4_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102067","volume":"57","author":"J Guo","year":"2020","unstructured":"Guo, J., et al.: A deep look into neural ranking models for information retrieval. Inf. Process. Manage. 57(6), 102067 (2020)","journal-title":"Inf. Process. Manage."},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Karpukhin, V.,et al.: Dense passage retrieval for open-domain question answering. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6769\u20136781. Association for Computational Linguistics, November 2020. https:\/\/aclanthology.org\/2020.emnlp-main.550","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Kobyli\u0144ski, \u0141., et al.: PolEval 2022\/23 challenge tasks and results. In: 2023 18th Conference on Computer Science and Intelligence Systems (FedCSIS), pp. 1237-1244. IEEE (2023)","DOI":"10.15439\/2023F5627"},{"key":"4_CR11","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR12","unstructured":"Li, H., Su, Y., Cai, D., Wang, Y., Liu, L.: A survey on retrieval-augmented text generation. arXiv preprint arXiv:2202.01110 (2022)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Ma, X., Wang, L., Yang, N., Wei, F., Lin, J.: Fine-tuning llama for multi-stage text retrieval. arXiv preprint arXiv:2310.08319 (2023)","DOI":"10.1145\/3626772.3657951"},{"key":"4_CR14","unstructured":"Mroczkowski, R., Rybak, P., Wr\u00f3blewska, A., Gawlik, I.: HerBERT: efficiently pretrained transformer-based language model for Polish. In: Babych, B., et al. (eds.) Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing, pp. 1\u201310. Association for Computational Linguistics, Kiyv, Ukraine, April 2021. https:\/\/aclanthology.org\/2021.bsnlp-1.1"},{"key":"4_CR15","unstructured":"Nogueira, R., Cho, K.: Passage re-ranking with Bert. arXiv preprint arXiv:1901.04085 (2019)"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Nogueira, R., Jiang, Z., Pradeep, R., Lin, J.: Document ranking with a pretrained sequence-to-sequence model. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 708\u2013718. Association for Computational Linguistics, November 2020. https:\/\/aclanthology.org\/2020.findings-emnlp.63","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"issue":"4","key":"4_CR17","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1561\/1500000019","volume":"3","author":"S Robertson","year":"2009","unstructured":"Robertson, S., Zaragoza, H., et al.: The probabilistic relevance framework: BM25 and beyond. Found. Trends\u00ae Inf. Retr. 3(4), 333\u2013389 (2009)","journal-title":"Found. Trends\u00ae Inf. Retr."},{"key":"4_CR18","unstructured":"Rosa, G., et al.: In defense of cross-encoders for zero-shot retrieval. arXiv preprint arXiv:2212.06121 (2022)"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Rybak, P.: Maupqa: Massive automatically-created polish question answering dataset. In: Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023), pp. 11\u201316 (2023)","DOI":"10.18653\/v1\/2023.bsnlp-1.2"},{"key":"4_CR20","unstructured":"Rybak, P., Ogrodniczuk, M.: SilverRetriever: advancing neural passage retrieval for polish question answering (2023)"},{"key":"4_CR21","unstructured":"Rybak, P., Przyby\u0142a, P., Ogrodniczuk, M.: Improving question answering performance through manual annotation: costs, benefits and strategies. arXiv preprint arXiv:2212.08897 (2022)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Sun, W., et al.: Is ChatGPT good at search? investigating large language models as re-ranking agents. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 14918\u201314937. Association for Computational Linguistics, Singapore, December 2023. https:\/\/aclanthology.org\/2023.emnlp-main.923","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"4_CR23","unstructured":"Thakur, N., Reimers, N., R\u00fcckl\u00e9, A., Srivastava, A., Gurevych, I.: Beir: A heterogeneous benchmark for zero-shot evaluation of information retrieval models. In: Vanschoren, J., Yeung, S. (eds.) Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, vol.\u00a01. Curran (2021). https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/65b9eea6e1cc6bb9f0cd2a47751a186f-Paper-round2.pdf"},{"key":"4_CR24","unstructured":"Wang, L., et al.: Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)"},{"key":"4_CR25","unstructured":"Wojtasik, K., Shishkin, V., Wo\u0142owiec, K., Janz, A., Piasecki, M.: BEIR-PL: Zero shot information retrieval benchmark for the polish language. arXiv preprint arXiv:2305.19840 (2023)"},{"key":"4_CR26","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighof, N.: C-pack: Packaged resources to advance general Chinese embedding. arXiv preprint arXiv:2309.07597 (2023)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: mT5: a massively multilingual pre-trained text-to-text transformer. In: Toutanova, K., et al. (eds.) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 483\u2013498. Association for Computational Linguistics, June 2021. https:\/\/aclanthology.org\/2021.naacl-main.41","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Yates, A., Nogueira, R., Lin, J.: Pretrained transformers for text ranking: Bert and beyond. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pp. 1154\u20131156 (2021)","DOI":"10.1145\/3437963.3441667"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, X., Ma, X., Shi, P., Lin, J.: Mr. TyDi: a multi-lingual benchmark for dense retrieval. In: Proceedings of the 1st Workshop on Multilingual Representation Learning, pp. 127\u2013137. Association for Computational Linguistics, Punta Cana, Dominican Republic, November 2021. https:\/\/aclanthology.org\/2021.mrl-1.12","DOI":"10.18653\/v1\/2021.mrl-1.12"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, X.: MIRACL: a multilingual Retrieval Dataset Covering 18 Diverse Languages. Trans. Assoc. Comput. Linguistics 11, 1114\u20131131 (2023). https:\/\/doi.org\/10.1162\/tacl_a_00595","DOI":"10.1162\/tacl_a_00595"},{"key":"4_CR31","unstructured":"Zhao, W.X., Liu, J., Ren, R., Wen, J.R.: Dense text retrieval based on pretrained language models: a survey. arXiv preprint arXiv:2211.14876 (2022)"},{"key":"4_CR32","unstructured":"Zhu, Y., et al.: Large language models for information retrieval: a survey. arXiv preprint arXiv:2308.07107 (2023)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Zhuang, H., et al.: Rankt5: fine-tuning t5 for text ranking with ranking losses. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2308\u20132313 (2023)","DOI":"10.1145\/3539618.3592047"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence and Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-84353-2_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T13:49:46Z","timestamp":1740491386000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-84353-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031843525","9783031843532"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-84353-2_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"17 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAISC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence and Soft Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zakopane","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icaisc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icaisc.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}