{"id":"https://openalex.org/W7168371879","doi":"https://doi.org/10.1145/3805712.3808621","title":"WebFAQ 2.0: A Multilingual QA Dataset with Mined Hard Negatives for Dense Retrieval","display_name":"WebFAQ 2.0: A Multilingual QA Dataset with Mined Hard Negatives for Dense Retrieval","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168371879","doi":"https://doi.org/10.1145/3805712.3808621"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808621","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808621","pdf_url":null,"source":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808621","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140835407","display_name":"Michael Dinzinger","orcid":"https://orcid.org/0009-0003-1747-5643"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Dinzinger","raw_affiliation_strings":["University of Passau, Passau, Germany"],"raw_orcid":"https://orcid.org/0009-0003-1747-5643","affiliations":[{"raw_affiliation_string":"University of Passau, Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140786536","display_name":"Laura Caspari","orcid":"https://orcid.org/0009-0002-6670-3211"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Laura Caspari","raw_affiliation_strings":["University of Passau, Passau, Germany"],"raw_orcid":"https://orcid.org/0009-0002-6670-3211","affiliations":[{"raw_affiliation_string":"University of Passau, Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140954061","display_name":"Ali Salman","orcid":"https://orcid.org/0009-0000-2422-6707"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ali Salman","raw_affiliation_strings":["University of Passau, Passau, Germany"],"raw_orcid":"https://orcid.org/0009-0000-2422-6707","affiliations":[{"raw_affiliation_string":"University of Passau, Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140890252","display_name":"Irvin Topi","orcid":"https://orcid.org/0009-0001-8298-5039"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Irvin Topi","raw_affiliation_strings":["University of Passau, Passau, Germany"],"raw_orcid":"https://orcid.org/0009-0001-8298-5039","affiliations":[{"raw_affiliation_string":"University of Passau, Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140954654","display_name":"Jelena Mitrovi\u0107","orcid":"https://orcid.org/0000-0003-3220-8749"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jelena Mitrovi\u0107","raw_affiliation_strings":["University of Passau, Passau, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3220-8749","affiliations":[{"raw_affiliation_string":"University of Passau, Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140891938","display_name":"Michael Granitzer","orcid":"https://orcid.org/0000-0003-3566-5507"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Granitzer","raw_affiliation_strings":["University of Passau, Passau, Germany and Interdisciplinary Transformation University, Linz, Austria"],"raw_orcid":"https://orcid.org/0000-0003-3566-5507","affiliations":[{"raw_affiliation_string":"University of Passau, Passau, Germany and Interdisciplinary Transformation University, Linz, Austria","institution_ids":["https://openalex.org/I186354981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I186354981"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3138","last_page":"3144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2833000123500824},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2822999954223633},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2782999873161316},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2558000087738037},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.2524999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6362000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4291999936103821},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.328900009393692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3808621","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808621","pdf_url":null,"source":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808621","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808621","pdf_url":null,"source":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2611029872","https://openalex.org/W2963626623","https://openalex.org/W3034469191","https://openalex.org/W3035497479","https://openalex.org/W3039695075","https://openalex.org/W3045462440","https://openalex.org/W3045958725","https://openalex.org/W3168875417","https://openalex.org/W3206996280","https://openalex.org/W3207095490","https://openalex.org/W4205103289","https://openalex.org/W4284689799","https://openalex.org/W4287018294","https://openalex.org/W4287645694","https://openalex.org/W4295682539","https://openalex.org/W4386576685","https://openalex.org/W4393090185","https://openalex.org/W4401306886","https://openalex.org/W4401306979","https://openalex.org/W4402670856","https://openalex.org/W4402856368","https://openalex.org/W4405655184","https://openalex.org/W4412394853","https://openalex.org/W4415092919","https://openalex.org/W4416034664","https://openalex.org/W6968445922"],"related_works":[],"abstract_inverted_index":{"We":[0,126],"introduce":[1],"WebFAQ":[2,9,52],"2.0,":[3],"a":[4,55,70,93,113],"new":[5],"version":[6],"of":[7,34],"the":[8,23,32,44,49],"dataset,":[10],"containing":[11],"198":[12],"million":[13],"FAQ-based":[14,46],"natural":[15],"question-answer":[16],"pairs":[17,38],"across":[18,104],"108":[19],"languages.":[20,106],"Compared":[21],"to":[22,39,87],"previous":[24],"version,":[25],"it":[26,43],"significantly":[27],"expands":[28],"multilingual":[29,75],"coverage":[30],"and":[31,63,74,83,117,145],"number":[33],"bilingual":[35],"aligned":[36],"QA":[37],"over":[40],"14.3M,":[41],"making":[42],"largest":[45],"resource.":[47],"Unlike":[48],"original":[50],"release,":[51],"2.0":[53],"uses":[54],"novel":[56],"data":[57],"collection":[58],"strategy":[59],"that":[60],"directly":[61],"crawls":[62],"extracts":[64],"relevant":[65],"web":[66],"content,":[67],"resulting":[68],"in":[69],"substantially":[71],"more":[72],"diverse":[73],"dataset":[76,96],"with":[77,101,142,148],"richer":[78],"context":[79],"through":[80],"page":[81],"titles":[82],"descriptions.":[84],"In":[85],"response":[86],"community":[88],"feedback,":[89],"we":[90],"also":[91],"release":[92],"hard":[94,108],"negatives":[95,109,123],"for":[97,121,137],"training":[98],"dense":[99,138],"retrievers,":[100],"1.25M":[102],"queries":[103],"20":[105],"These":[107],"were":[110],"mined":[111],"using":[112],"two-stage":[114],"retrieval":[115],"pipeline":[116],"include":[118],"cross-encoder":[119],"scores":[120],"200":[122],"per":[124],"query.":[125],"further":[127],"show":[128],"how":[129],"this":[130],"resource":[131],"enables":[132],"two":[133],"primary":[134],"fine-tuning":[135],"strategies":[136],"retrievers:":[139],"Contrastive":[140],"Learning":[141],"MultipleNegativesRanking":[143],"loss,":[144],"Knowledge":[146],"Distillation":[147],"MarginMSE":[149],"loss.":[150]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-16T00:00:00"}