{"id":"https://openalex.org/W4385573258","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.357","title":"DuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine","display_name":"DuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385573258","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.357"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.emnlp-main.357","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.357","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.357","pdf_url":"https://aclanthology.org/2022.emnlp-main.357.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.emnlp-main.357.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067879712","display_name":"Yifu Qiu","orcid":"https://orcid.org/0000-0001-5645-3189","observed_orcids":["https://orcid.org/0000-0001-5645-3189"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yifu Qiu","raw_affiliation_strings":["Institute for Language, Cognition and Computation, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language, Cognition and Computation, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402304","display_name":"Hongyu Li","orcid":"https://orcid.org/0000-0002-6518-9866","observed_orcids":["https://orcid.org/0000-0002-6518-9866"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Li","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021663654","display_name":"Yingqi Qu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingqi Qu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027016896","display_name":"Ying Chen","orcid":"https://orcid.org/0000-0002-1914-8780","observed_orcids":["https://orcid.org/0000-0002-1914-8780","https://orcid.org/0000-0002-2577-7348","https://orcid.org/0009-0005-5793-0991"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Chen","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075964362","display_name":"Qiaoqiao She","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"QiaoQiao She","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375105","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-1727-6321","observed_orcids":["https://orcid.org/0000-0003-1727-6321"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072316347","display_name":"Hua Yue Wu","orcid":"https://orcid.org/0000-0002-0401-2434","observed_orcids":["https://orcid.org/0000-0002-0401-2434"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Wu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386394","display_name":"Haifeng Wang","orcid":"https://orcid.org/0000-0002-0672-7468","observed_orcids":["https://orcid.org/0000-0002-0672-7468"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haifeng Wang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100386394"],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":2.0115,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.89236915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5326","last_page":"5338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9976000189781189,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9976000189781189,"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/T10028","display_name":"Topic Modeling","score":0.0015999999595806003,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/passage-retrieval","display_name":"passage retrieval","score":0.878000020980835},{"id":"https://openalex.org/keywords/search-engines","display_name":"search engines","score":0.6620000004768372},{"id":"https://openalex.org/keywords/domain-generalization","display_name":"domain generalization","score":0.753000020980835},{"id":"https://openalex.org/keywords/cross-lingual-information-retrieval","display_name":"cross-lingual information retrieval","score":0.9649999737739563},{"id":"https://openalex.org/keywords/dense-retrievers","display_name":"dense retrievers","score":0.7710000276565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8652585744857788},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7716185450553894},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5744577050209045},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5346236824989319},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5187759399414062},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.5086468458175659},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5058686137199402},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.46358323097229004},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.41430169343948364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3589220941066742},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2022.emnlp-main.357","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.357","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.357","pdf_url":"https://aclanthology.org/2022.emnlp-main.357.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.10232","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.10232","pdf_url":"https://arxiv.org/pdf/2203.10232","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2203.10232","doi":"https://doi.org/10.48550/arxiv.2203.10232","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.10232","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.emnlp-main.357","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.357","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.357","pdf_url":"https://aclanthology.org/2022.emnlp-main.357.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385573258.pdf","grobid_xml":"https://content.openalex.org/works/W4385573258.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1978394996","https://openalex.org/W2037140704","https://openalex.org/W2130618701","https://openalex.org/W2252136820","https://openalex.org/W2593864460","https://openalex.org/W2612431505","https://openalex.org/W2798598599","https://openalex.org/W2903314293","https://openalex.org/W2912924812","https://openalex.org/W2937036051","https://openalex.org/W2938830017","https://openalex.org/W2945127593","https://openalex.org/W2951534261","https://openalex.org/W2952370363","https://openalex.org/W2954475589","https://openalex.org/W2963341956","https://openalex.org/W2963957489","https://openalex.org/W2965373594","https://openalex.org/W2996064239","https://openalex.org/W3014367186","https://openalex.org/W3015883388","https://openalex.org/W3021397474","https://openalex.org/W3021636956","https://openalex.org/W3047026265","https://openalex.org/W3101279614","https://openalex.org/W3105949871","https://openalex.org/W3118668786","https://openalex.org/W3155895380","https://openalex.org/W3157758108","https://openalex.org/W3168875417","https://openalex.org/W3169937871","https://openalex.org/W3176182290","https://openalex.org/W3185042171","https://openalex.org/W3188983256","https://openalex.org/W3196754070","https://openalex.org/W3198713493","https://openalex.org/W3214364360","https://openalex.org/W4220818323","https://openalex.org/W4224923650","https://openalex.org/W4252076394","https://openalex.org/W4286905174","https://openalex.org/W4385574176"],"related_works":["https://openalex.org/W4224939811","https://openalex.org/W4284678164","https://openalex.org/W4387619806","https://openalex.org/W2125597039","https://openalex.org/W2769934148","https://openalex.org/W4402671753","https://openalex.org/W7128018186","https://openalex.org/W1512891149","https://openalex.org/W4384641500","https://openalex.org/W2114279702"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,44,79],"present":[4],"DuReader":[5,105],"retrieval":[6,15,100,106,144],",":[7],"a":[8,27,91,110],"large-scale":[9],"Chinese":[10],"dataset":[11],"for":[12,85,97,98],"passage":[13],"retrieval.DuReader":[14],"contains":[16],"more":[17],"than":[18],"90K":[19],"queries":[20,68,96,127],"and":[21,37,52,63,76,109,122,128,142],"over":[22],"8M":[23],"unique":[24],"passages":[25],"from":[26,60],"commercial":[28],"search":[29],"engine.To":[30],"alleviate":[31],"the":[32,39,47,66,74,118,123],"shortcomings":[33],"of":[34,41,93,112],"other":[35],"datasets":[36],"ensure":[38],"quality":[40],"our":[42],"benchmark,":[43],"(1)":[45],"reduce":[46],"false":[48],"negatives":[49],"in":[50],"development":[51,75],"test":[53],"sets":[54,84],"by":[55],"manually":[56],"annotating":[57],"results":[58],"pooled":[59],"multiple":[61],"retrievers,":[62],"(2)":[64],"remove":[65],"training":[67],"that":[69,104,133],"are":[70],"semantically":[71],"similar":[72],"to":[73],"testing":[77,83],"queries.Additionally,":[78],"provide":[80],"two":[81],"outof-domain":[82],"cross-domain":[86],"evaluation,":[87],"as":[88,90,117],"well":[89,139],"set":[92],"human":[94],"translated":[95],"cross-lingual":[99,143],"evaluation.The":[101],"experiments":[102,130],"demonstrate":[103],"is":[107,145],"challenging":[108],"number":[111],"problems":[113],"remain":[114],"unsolved,":[115],"such":[116],"salient":[119],"phrase":[120],"mismatch":[121,125],"syntactic":[124],"between":[126],"paragraphs.These":[129],"also":[131],"show":[132],"dense":[134],"retrievers":[135],"do":[136],"not":[137],"generalize":[138],"across":[140],"domains,":[141],"essentially":[146],"challenging.DuReader":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}