{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T06:09:32Z","timestamp":1777615772921,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Grant Agency of the Czech Republic","award":["GX20-16819X"],"award-info":[{"award-number":["GX20-16819X"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657851","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"1221-1231","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["CWRCzech: 100M Query-Document Czech Click Dataset and Its Application to Web Relevance Ranking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9429-9278","authenticated-orcid":false,"given":"Josef","family":"Von\u00e1sek","sequence":"first","affiliation":[{"name":"Seznam.cz, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3295-5576","authenticated-orcid":false,"given":"Milan","family":"Straka","sequence":"additional","affiliation":[{"name":"Charles University, Faculty of Mathematics and Physics, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6772-2575","authenticated-orcid":false,"given":"Rostislav","family":"Kr\u010d","sequence":"additional","affiliation":[{"name":"Seznam.cz, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7524-0367","authenticated-orcid":false,"given":"Lenka","family":"Lasonov\u00e1","sequence":"additional","affiliation":[{"name":"Seznam.cz, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5398-4371","authenticated-orcid":false,"given":"Ekaterina","family":"Egorova","sequence":"additional","affiliation":[{"name":"Seznam.cz, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0075-2408","authenticated-orcid":false,"given":"Jana","family":"Strakov\u00e1","sequence":"additional","affiliation":[{"name":"Charles University, Faculty of Mathematics and Physics, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2259-1377","authenticated-orcid":false,"given":"Jakub","family":"N\u00e1plava","sequence":"additional","affiliation":[{"name":"Seznam.cz, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209986"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3274274"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Zeynep Akkalyoncu Yilmaz Shengjin Wang Wei Yang Haotian Zhang and Jimmy Lin. 2019. Applying BERT to Document Retrieval with Birch. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLPIJCNLP): System Demonstrations Sebastian Pad\u00f3 and Ruihong Huang (Eds.). Association for Computational Linguistics Hong Kong China 19--24. https: \/\/doi.org\/10.18653\/v1\/D19-3004","DOI":"10.18653\/v1\/D19-3004"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","unstructured":"2024. Some Like It Small: Czech Semantic Embedding Models for Industry Applications. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 22734--22742."},{"key":"e_1_3_2_1_5_1","volume-title":"Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm. CoRR abs\/2108.05652","author":"Bo Lin","year":"2021","unstructured":"Lin Bo, Liang Pang, Gang Wang, Jun Xu, XiuQiang He, and Ji-Rong Wen. 2021. Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm. CoRR abs\/2108.05652 (2021). arXiv:2108.05652 https:\/\/arxiv.org\/abs\/2108.05652"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/792550.792552"},{"key":"e_1_3_2_1_7_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_8_1","volume-title":"Click Models for Web Search","author":"Chuklin Aleksandr","unstructured":"Aleksandr Chuklin, Ilya Markov, and Maarten Rijke. 2015. Click Models for Web Search. Springer International Publishing, Cham, Switzerland. https:\/\/link.springer.com\/book\/10.1007\/978-3-031-02294-4#bibliographic-information"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412779"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331303"},{"key":"e_1_3_2_1_11_1","first-page":"19","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Jill Burstein, Christy Doran, and Thamar Solorio (Eds.). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186. https:\/\/doi. org\/10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1198\/000313002753631385"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2009.tm08368"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1049"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556220"},{"key":"e_1_3_2_1_17_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21502"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89579-2_3"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600088"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331317"},{"key":"e_1_3_2_1_22_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. (November","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. (November 2016). https:\/\/www.microsoft.com\/en-us\/research\/publication\/ms-marco-humangenerated-machine-reading-comprehension-dataset\/"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"e_1_3_2_1_24_1","volume-title":"Lin","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, and Jimmy J. Lin. 2019. Multi-Stage Document Ranking with BERT. ArXiv abs\/1910.14424 (2019). https: \/\/api.semanticscholar.org\/CorpusID:207758365"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1146847.1146848"},{"key":"e_1_3_2_1_26_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463242"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of The Third Text REtrieval Conference, TREC 1994","author":"Robertson Stephen E.","year":"1994","unstructured":"Stephen E. Robertson, Steve Walker, Susan Jones, Micheline Hancock-Beaulieu, and Mike Gatford. 1994. Okapi at TREC-3. In Proceedings of The Third Text REtrieval Conference, TREC 1994, Gaithersburg, Maryland, USA, November 2-4, 1994 (NIST Special Publication, Vol. 500--225), Donna K. Harman (Ed.). National Institute of Standards and Technology (NIST), 109--126. http:\/\/trec.nist.gov\/pubs\/ trec3\/papers\/city.ps.gz"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556207"},{"key":"e_1_3_2_1_30_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H.Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/ 2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3584624"},{"key":"e_1_3_2_1_32_1","unstructured":"Xiaohui Xie Qian Dong Bingning Wang Feiyang Lv Ting Yao Weinan Gan Zhijing Wu Xiangsheng Li Haitao Li Yiqun Liu and Jin Ma. 2023. T2Ranking: A large-scale Chinese Benchmark for Passage Ranking. arXiv:2304.03679 [cs.IR]"},{"key":"e_1_3_2_1_33_1","volume-title":"Yajun Wang, Guangzhong Sun, and Xing Xie.","author":"Yang Junhan","year":"2021","unstructured":"Junhan Yang, Zheng Liu, Bowen Jin, Jianxun Lian, Defu Lian, Akshay Soni, Eun Yong Kang, Yajun Wang, Guangzhong Sun, and Xing Xie. 2021. Hybrid Encoder: Towards Efficient and Precise Native Ads Recommendation via Hybrid Transformer Encoding Networks. CoRR abs\/2104.10925 (2021). arXiv:2104.10925 https:\/\/arxiv.org\/abs\/2104.10925"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450129"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645724"},{"key":"e_1_3_2_1_36_1","first-page":"1","article-title":"Some Observations on User Search","volume":"9","author":"Zhang Yuye","year":"2006","unstructured":"Yuye Zhang and Alistair Moffat. 2006. Some Observations on User Search Behaviour. Aust. J. Intell. Inf. Process. Syst. 9, 2 (2006), 1--8.","journal-title":"Behaviour. Aust. J. Intell. Inf. Process. Syst."},{"key":"e_1_3_2_1_37_1","unstructured":"Wayne Xin Zhao Jing Liu Ruiyang Ren and Ji-Rong Wen. 2022. Dense Text Retrieval based on Pretrained Language Models: A Survey. arXiv:2211.14876 [cs.IR]"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210092"},{"key":"e_1_3_2_1_39_1","volume-title":"Oh (Eds.)","volume":"35","author":"Zou Lixin","year":"2022","unstructured":"Lixin Zou, Haitao Mao, Xiaokai Chu, Jiliang Tang,Wenwen Ye, ShuaiqiangWang, and Dawei Yin. 2022. A Large Scale Search Dataset for Unbiased Learning to Rank. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 1127--1139. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/07f560092a0edceabf55af32a40eaee3-Paper-Datasets_and_Benchmarks.pdf"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657851","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:18:43Z","timestamp":1755839923000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657851"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":39,"alternative-id":["10.1145\/3626772.3657851","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657851","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}