{"id":"https://openalex.org/W4400530882","doi":"https://doi.org/10.1145/3626772.3657850","title":"Revisiting Document Expansion and Filtering for Effective First-Stage Retrieval","display_name":"Revisiting Document Expansion and Filtering for Effective First-Stage Retrieval","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400530882","doi":"https://doi.org/10.1145/3626772.3657850"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657850","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657850","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":"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/A5051977375","display_name":"Watheq Mansour","orcid":"https://orcid.org/0000-0002-9463-595X"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Watheq Mansour","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9463-595X","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012958162","display_name":"Shengyao Zhuang","orcid":"https://orcid.org/0000-0002-6711-0955"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shengyao Zhuang","raw_affiliation_strings":["CSIRO, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6711-0955","affiliations":[{"raw_affiliation_string":"CSIRO, Brisbane, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076031002","display_name":"Guido Zuccon","orcid":"https://orcid.org/0000-0003-0271-5563"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guido Zuccon","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0271-5563","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070739676","display_name":"Joel Mackenzie","orcid":"https://orcid.org/0000-0001-7992-4633"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Joel Mackenzie","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7992-4633","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051977375"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":2.238,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90153382,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"186","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9976999759674072,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.6606180667877197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6381949186325073},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6057758331298828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3217433989048004},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.14266163110733032}],"concepts":[{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.6606180667877197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6381949186325073},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6057758331298828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3217433989048004},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.14266163110733032},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3657850","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657850","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1791987072","https://openalex.org/W1984565341","https://openalex.org/W2000431947","https://openalex.org/W2006996936","https://openalex.org/W2048978851","https://openalex.org/W2065472179","https://openalex.org/W2077948748","https://openalex.org/W2117473841","https://openalex.org/W2126485285","https://openalex.org/W2129632406","https://openalex.org/W2129971563","https://openalex.org/W2138662031","https://openalex.org/W2149768609","https://openalex.org/W2159665776","https://openalex.org/W2159859920","https://openalex.org/W2160555926","https://openalex.org/W2164052363","https://openalex.org/W2292193262","https://openalex.org/W2336445533","https://openalex.org/W2336806308","https://openalex.org/W2530530386","https://openalex.org/W2740492458","https://openalex.org/W2741307002","https://openalex.org/W2928384811","https://openalex.org/W2963096510","https://openalex.org/W2981852735","https://openalex.org/W3015713034","https://openalex.org/W3021397474","https://openalex.org/W3021779606","https://openalex.org/W3023238803","https://openalex.org/W3034521898","https://openalex.org/W3036320503","https://openalex.org/W3045745713","https://openalex.org/W3094368983","https://openalex.org/W3098468692","https://openalex.org/W3099384026","https://openalex.org/W3100107515","https://openalex.org/W3101346938","https://openalex.org/W3103686454","https://openalex.org/W3104914963","https://openalex.org/W3128581554","https://openalex.org/W3133594109","https://openalex.org/W3134665270","https://openalex.org/W3147292006","https://openalex.org/W3152624702","https://openalex.org/W3154280800","https://openalex.org/W3154755316","https://openalex.org/W3155114168","https://openalex.org/W3156166379","https://openalex.org/W3172119680","https://openalex.org/W3175111331","https://openalex.org/W3196754070","https://openalex.org/W3198431451","https://openalex.org/W3198691721","https://openalex.org/W3209981429","https://openalex.org/W4205951122","https://openalex.org/W4225372933","https://openalex.org/W4226391416","https://openalex.org/W4252076394","https://openalex.org/W4284699573","https://openalex.org/W4284706395","https://openalex.org/W4284880643","https://openalex.org/W4288089799","https://openalex.org/W4296873212","https://openalex.org/W4311609640","https://openalex.org/W4327499170","https://openalex.org/W4327644554","https://openalex.org/W4384652592","https://openalex.org/W4384891026","https://openalex.org/W4385562603"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Document":[0],"expansion":[1,31,86,169],"is":[2,145],"a":[3,35,72,124,158],"technique":[4],"that":[5,33,43,102,143],"aims":[6],"to":[7,29,38,48,78,84,136],"reduce":[8],"the":[9,30,49,54,57,62,81,93,97,116,162,173],"likelihood":[10],"of":[11,56,64,76,161,166],"term":[12,149],"mismatch":[13],"by":[14],"augmenting":[15],"documents":[16],"with":[17,123],"related":[18],"terms":[19],"or":[20],"queries.":[21],"Doc2Query":[22],"minus":[23,24],"(Doc2Query-)":[25],"represents":[26],"an":[27],"extension":[28],"process":[32,119],"uses":[34],"neural":[36],"model":[37],"identify":[39],"and":[40,87,141,164,171],"remove":[41],"expansions":[42],"may":[44],"not":[45,146],"be":[46,121,152],"relevant":[47],"given":[50],"document,":[51],"thereby":[52],"increasing":[53],"quality":[55],"ranking":[58],"while":[59],"simultaneously":[60],"reducing":[61],"amount":[63],"augmented":[65],"data.":[66],"In":[67],"this":[68],"work,":[69],"we":[70,100,113,132],"conduct":[71],"detailed":[73],"reproducibility":[74],"study":[75],"Doc2Query-":[77,98],"better":[79],"understand":[80],"trade-offs":[82],"inherent":[83],"document":[85,168],"filtering":[88,103,144],"mechanisms.":[89],"After":[90],"successfully":[91],"reproducing":[92],"best-performing":[94],"method":[95],"from":[96],"family,":[99],"show":[101],"actually":[104],"harms":[105],"recall-based":[106],"metrics":[107],"on":[108],"various":[109],"test":[110],"collections.":[111],"Next,":[112],"explore":[114],"whether":[115],"two-stage":[117],"\"generate-then-filter\"":[118],"can":[120,151],"replaced":[122],"single":[125],"generation":[126],"phase":[127],"via":[128],"reinforcement":[129],"learning.":[130],"Finally,":[131],"extend":[133],"our":[134,155],"experimentation":[135],"learned":[137],"sparse":[138],"retrieval":[139],"models":[140],"demonstrate":[142],"helpful":[147],"when":[148],"weights":[150],"learned.":[153],"Overall,":[154],"work":[156],"provides":[157],"deeper":[159],"understanding":[160],"behaviour":[163],"characteristics":[165],"common":[167],"mechanisms,":[170],"paves":[172],"way":[174],"for":[175],"developing":[176],"more":[177],"efficient":[178],"yet":[179],"effective":[180],"augmentation":[181],"models.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}