{"id":"https://openalex.org/W4399317933","doi":"https://doi.org/10.1145/3626772.3657851","title":"CWRCzech: 100M Query-Document Czech Click Dataset and Its Application to Web Relevance Ranking","display_name":"CWRCzech: 100M Query-Document Czech Click Dataset and Its Application to Web Relevance Ranking","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4399317933","doi":"https://doi.org/10.1145/3626772.3657851"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.20994","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099010559","display_name":"Josef Von\u00e1\u0161ek","orcid":"https://orcid.org/0009-0006-9429-9278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Josef Von\u00e1sek","raw_affiliation_strings":["Seznam.cz, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0009-0006-9429-9278","affiliations":[{"raw_affiliation_string":"Seznam.cz, Prague, Czech Republic","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060081515","display_name":"Milan Straka","orcid":"https://orcid.org/0000-0003-3295-5576"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Milan Straka","raw_affiliation_strings":["Charles University, Faculty of Mathematics and Physics, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0003-3295-5576","affiliations":[{"raw_affiliation_string":"Charles University, Faculty of Mathematics and Physics, Prague, Czech Republic","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113238901","display_name":"Rostislav Kr\u010d","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rostislav Kr\u010d","raw_affiliation_strings":["Seznam.cz, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0001-6772-2575","affiliations":[{"raw_affiliation_string":"Seznam.cz, Prague, Czech Republic","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099010560","display_name":"Lenka Laso\u0148ov\u00e1","orcid":"https://orcid.org/0009-0003-7524-0367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lenka Lasonov\u00e1","raw_affiliation_strings":["Seznam.cz, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0009-0003-7524-0367","affiliations":[{"raw_affiliation_string":"Seznam.cz, Prague, Czech Republic","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ekaterina Egorova","orcid":"https://orcid.org/0000-0001-5398-4371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ekaterina Egorova","raw_affiliation_strings":["Seznam.cz, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0001-5398-4371","affiliations":[{"raw_affiliation_string":"Seznam.cz, Prague, Czech Republic","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jana Strakov\u00e1","orcid":"https://orcid.org/0000-0003-0075-2408"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jana Strakov\u00e1","raw_affiliation_strings":["Charles University, Faculty of Mathematics and Physics, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0003-0075-2408","affiliations":[{"raw_affiliation_string":"Charles University, Faculty of Mathematics and Physics, Prague, Czech Republic","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032425414","display_name":"Jakub N\u00e1plava","orcid":"https://orcid.org/0000-0003-2259-1377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakub N\u00e1plava","raw_affiliation_strings":["Seznam.cz, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0003-2259-1377","affiliations":[{"raw_affiliation_string":"Seznam.cz, Prague, Czech Republic","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.298,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8386351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1221","last_page":"1231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9602000117301941,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9602000117301941,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9550999999046326,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9485999941825867,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.8565495610237122},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7899739146232605},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.7708752155303955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7429995536804199},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6644869446754456},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.49785757064819336},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4087240397930145},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.22584134340286255},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.04350382089614868}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.8565495610237122},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7899739146232605},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.7708752155303955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429995536804199},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6644869446754456},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.49785757064819336},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4087240397930145},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.22584134340286255},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.04350382089614868},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626772.3657851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.20994","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.20994","pdf_url":"https://arxiv.org/pdf/2405.20994","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.20994","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.20994","pdf_url":"https://arxiv.org/pdf/2405.20994","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6528905359","display_name":"Language Understanding: from Syntax to Discourse","funder_award_id":"GX20-16819X","funder_id":"https://openalex.org/F4320321006","funder_display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky"}],"funders":[{"id":"https://openalex.org/F4320321006","display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","ror":"https://ror.org/01pv73b02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399317933.pdf","grobid_xml":"https://content.openalex.org/works/W4399317933.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1974790883","https://openalex.org/W1982858363","https://openalex.org/W2034669660","https://openalex.org/W2062918108","https://openalex.org/W2069870183","https://openalex.org/W2106576032","https://openalex.org/W2156037541","https://openalex.org/W2166237624","https://openalex.org/W2797400361","https://openalex.org/W2798598599","https://openalex.org/W2897785891","https://openalex.org/W2940927814","https://openalex.org/W2945127593","https://openalex.org/W2963341956","https://openalex.org/W2987249037","https://openalex.org/W3064953855","https://openalex.org/W3093655911","https://openalex.org/W3100107515","https://openalex.org/W3133376386","https://openalex.org/W3136473512","https://openalex.org/W3207988762","https://openalex.org/W4283790703","https://openalex.org/W4367310110"],"related_works":["https://openalex.org/W2053591227","https://openalex.org/W2581240705","https://openalex.org/W2041353081","https://openalex.org/W2568183987","https://openalex.org/W2118564381","https://openalex.org/W1967370444","https://openalex.org/W2150136235","https://openalex.org/W2163901716","https://openalex.org/W2152204162","https://openalex.org/W2739821120"],"abstract_inverted_index":{"We":[0],"present":[1],"CWRCzech,":[2],"Click":[3],"Web":[4],"Ranking":[5],"dataset":[6,14,40],"for":[7,15,79],"Czech,":[8],"a":[9,74],"100M":[10],"query-document":[11,86],"Czech":[12,77],"click":[13,39],"relevance":[16,81,104],"ranking":[17,105],"with":[18,41],"user":[19,60,100],"behavior":[20,101],"data":[21,102,112],"collected":[22],"from":[23],"search":[24,53],"engine":[25],"logs":[26],"of":[27,32,122],"Seznam.cz.":[28],"To":[29],"the":[30,37,52,80,99,120,141],"best":[31],"our":[33],"knowledge,":[34],"CWRCzech":[35,129],"is":[36,130,138],"largest":[38],"raw":[42],"text":[43],"published":[44,131],"so":[45],"far.":[46],"It":[47],"provides":[48],"document":[49],"positions":[50],"in":[51],"results":[54],"as":[55,57],"well":[56],"information":[58],"about":[59],"behavior:":[61],"27.6M":[62],"clicked":[63],"documents":[64],"and":[65,106,137],"10.8M":[66],"dwell":[67],"times.":[68],"In":[69],"addition,":[70],"we":[71,96],"also":[72],"publish":[73],"manually":[75],"annotated":[76,89,127],"test":[78],"task,":[82],"containing":[83],"nearly":[84],"50k":[85],"pairs,":[87],"each":[88],"by":[90],"at":[91,115,144],"least":[92],"2":[93],"annotators.":[94],"Finally,":[95],"analyze":[97],"how":[98],"improve":[103],"show":[107],"that":[108],"models":[109,123],"trained":[110,124],"on":[111,125],"automatically":[113],"harnessed":[114],"sufficient":[116],"scale":[117],"can":[118],"surpass":[119],"performance":[121],"human":[126],"data.":[128],"under":[132],"an":[133],"academic":[134],"non-commercial":[135],"license":[136],"available":[139],"to":[140],"research":[142],"community":[143],"https://github.com/seznam/CWRCzech.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2024-06-04T00:00:00"}