{"id":"https://openalex.org/W4387846449","doi":"https://doi.org/10.1145/3583780.3615129","title":"RePair: An Extensible Toolkit to Generate Large-Scale Datasets for Query Refinement via Transformers","display_name":"RePair: An Extensible Toolkit to Generate Large-Scale Datasets for Query Refinement via Transformers","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387846449","doi":"https://doi.org/10.1145/3583780.3615129"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615129","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3583780.3615129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093105946","display_name":"Yogeswar Lakshmi Narayanan","orcid":"https://orcid.org/0009-0002-3197-7773"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Yogeswar Lakshmi Narayanan","raw_affiliation_strings":["University of Windsor, Windsor, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Windsor, Windsor, ON, Canada","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019367061","display_name":"Hossein Fani","orcid":"https://orcid.org/0000-0002-6033-6564"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hossein Fani","raw_affiliation_strings":["University of Windsor, Windsor, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Windsor, Windsor, ON, Canada","institution_ids":["https://openalex.org/I74413500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093105946"],"corresponding_institution_ids":["https://openalex.org/I74413500"],"apc_list":null,"apc_paid":null,"fwci":0.9178,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80658892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"898","issue":null,"first_page":"5376","last_page":"5380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"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":0.9983000159263611,"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/T11719","display_name":"Data Quality and Management","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9926000237464905,"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/computer-science","display_name":"Computer science","score":0.8692226409912109},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7219890356063843},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6246187090873718},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5612767934799194},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5590941905975342},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5419711470603943},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.52376788854599},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48597419261932373},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46070992946624756},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.4466686546802521},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.43819183111190796},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4245876669883728},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.41632890701293945},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.32697978615760803},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16330701112747192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8692226409912109},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7219890356063843},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6246187090873718},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5612767934799194},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5590941905975342},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5419711470603943},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.52376788854599},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48597419261932373},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46070992946624756},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.4466686546802521},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.43819183111190796},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4245876669883728},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.41632890701293945},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.32697978615760803},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16330701112747192},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3615129","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3583780.3615129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1982858363","https://openalex.org/W1993378086","https://openalex.org/W2096961418","https://openalex.org/W2578506968","https://openalex.org/W2741609678","https://openalex.org/W2745673470","https://openalex.org/W3021397474","https://openalex.org/W3035085156","https://openalex.org/W3093483562","https://openalex.org/W3180230246","https://openalex.org/W3208981019","https://openalex.org/W4284708952","https://openalex.org/W4287670436"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2572349046","https://openalex.org/W2901901036","https://openalex.org/W2026738364","https://openalex.org/W3125756434","https://openalex.org/W2146885082","https://openalex.org/W2538384344","https://openalex.org/W3049728138","https://openalex.org/W2184296057","https://openalex.org/W2100181111"],"abstract_inverted_index":{"Query":[0],"refinement":[1],"is":[2,50,160],"the":[3,17,84,131,136,142,168,190],"process":[4],"of":[5,19,73,92,125,128,141,167,183],"transforming":[6],"users'":[7,34],"queries":[8,36,93],"into":[9],"newrefined":[10],"versions":[11,124],"without":[12],"semantic":[13,86],"drift":[14],"to":[15,66,81,150],"enhance":[16],"relevance":[18,96,132],"search":[20,39],"results.":[21],"Prior":[22],"query":[23,29,157,186],"refiners":[24],"were":[25],"benchmarked":[26],"on":[27,189],"web":[28],"logs":[30],"followingweak":[31],"assumptions":[32],"that":[33],"input":[35,156],"within":[37],"a":[38,43,90,102],"session":[40],"are":[41],"about":[42],"single":[44],"topic":[45],"and":[46,94,113,121,159,176],"improve":[47],"gradually,":[48],"which":[49,129],"not":[51],"necessarily":[52],"accurate":[53],"in":[54,83,139,164],"practice.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"contribute":[60],"RePair,":[61],"an":[62,114],"open-source":[63],"configurable":[64],"toolkit":[65],"generatelarge-scale":[67],"gold-standard":[68,152,172],"benchmark":[69,181],"datasets":[70,153,173,192],"whose":[71],"pairs":[72],"(original":[74],"query,":[75],"refined":[76,123],"versions)":[77],"arealmost":[78],"surely":[79],"guaranteed":[80],"be":[82],"same":[85],"context.":[87],"RePair":[88,145,170],"takes":[89],"dataset":[91],"their":[95],"judgements":[97],"(e.g.,":[98,108,117],"msmarco":[99],"or":[100,104,110,119],"aol),":[101],"sparse":[103],"dense":[105],"retrieval":[106,137],"method":[107,138],"bm25":[109],"colbert":[111],"),":[112],"evaluation":[115,143],"metric":[116],"map":[118],"mrr),":[120],"outputs":[122],"queries,":[126],"each":[127],"with":[130,162],"improvement":[133],"guarantees":[134],"under":[135],"terms":[140],"metric.":[144],"benefits":[146],"from":[147],"text-to-text-transfer-transformer":[148],"(t5)":[149],"generate":[151],"for":[154,174],"any":[155],"sets":[158],"designed":[161],"extensibility":[163],"mind.":[165],"Out":[166],"box,":[169],"includes":[171],"aol":[175],"msmarco.passage":[177],"as":[178,180],"well":[179],"results":[182],"state-of-the-art":[184],"supervised":[185],"suggestion":[187],"methods":[188],"generated":[191],"at":[193],"https://github.com/fani-lab/RePair.":[194]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}