{"id":"https://openalex.org/W4283315779","doi":"https://doi.org/10.48550/arxiv.2206.10128","title":"Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation","display_name":"Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation","publication_year":2022,"publication_date":"2022-06-21","ids":{"openalex":"https://openalex.org/W4283315779","doi":"https://doi.org/10.48550/arxiv.2206.10128"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.10128","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.10128","pdf_url":"https://arxiv.org/pdf/2206.10128","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.10128","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012958162","display_name":"Shengyao Zhuang","orcid":"https://orcid.org/0000-0002-6711-0955","observed_orcids":["https://orcid.org/0000-0002-6711-0955"]},"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":"Zhuang, Shengyao","raw_affiliation_strings":["Taipei , Taiwan","The University of Queensland Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taipei , Taiwan","institution_ids":[]},{"raw_affiliation_string":"The University of Queensland Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085999236","display_name":"Houxing Ren","orcid":"https://orcid.org/0000-0001-9750-1626","observed_orcids":["https://orcid.org/0000-0001-9750-1626"]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren, Houxing","raw_affiliation_strings":["Beihang University China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077262995","display_name":"Linjun Shou","orcid":"https://orcid.org/0000-0002-1050-7708","observed_orcids":["https://orcid.org/0000-0002-1050-7708"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shou, Linjun","raw_affiliation_strings":["Microsoft STCA China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062247330","display_name":"Jian Pei","orcid":"https://orcid.org/0000-0002-2200-8711","observed_orcids":["https://orcid.org/0000-0002-2200-8711"]},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pei, Jian","raw_affiliation_strings":["Simon Fraser University Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gong, Ming","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong, Ming","raw_affiliation_strings":["Microsoft STCA China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076031002","display_name":"Guido Zuccon","orcid":"https://orcid.org/0000-0003-0271-5563","observed_orcids":["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":"Zuccon, Guido","raw_affiliation_strings":["The University of Queensland Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060116992","display_name":"Daxin Jiang","orcid":"https://orcid.org/0000-0002-6657-5806","observed_orcids":["https://orcid.org/0000-0002-6657-5806"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Daxin","raw_affiliation_strings":["Microsoft STCA China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":108,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9692000150680542,"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":0.9692000150680542,"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":0.02669999934732914,"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":0.0007999999797903001,"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/query-generation","display_name":"query generation","score":0.7620000243186951},{"id":"https://openalex.org/keywords/cross-lingual-information-retrieval","display_name":"cross-lingual information retrieval","score":0.9769999980926514},{"id":"https://openalex.org/keywords/passage-retrieval","display_name":"passage retrieval","score":0.7419999837875366},{"id":"https://openalex.org/keywords/cross-encoder-reranking","display_name":"cross-encoder reranking","score":0.8539999723434448},{"id":"https://openalex.org/keywords/document-representation","display_name":"document representation","score":0.4950000047683716}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8955975770950317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166619539260864},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7862436771392822},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6728930473327637},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5338718891143799},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.517198920249939},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3445481061935425},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09966418147087097},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2206.10128","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.10128","pdf_url":"https://arxiv.org/pdf/2206.10128","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.2206.10128","doi":"https://doi.org/10.48550/arxiv.2206.10128","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.10128","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":"pmh:oai:arXiv.org:2206.10128","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.10128","pdf_url":"https://arxiv.org/pdf/2206.10128","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283315779.pdf","grobid_xml":"https://content.openalex.org/works/W4283315779.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2981852735","https://openalex.org/W2982596739","https://openalex.org/W3093955333","https://openalex.org/W3134642945","https://openalex.org/W3174203100","https://openalex.org/W3193367516","https://openalex.org/W3210904070","https://openalex.org/W4281259526","https://openalex.org/W7133197669","https://openalex.org/W7133208784"],"related_works":["https://openalex.org/W4385565194","https://openalex.org/W7133208784","https://openalex.org/W7212053616","https://openalex.org/W4385567756","https://openalex.org/W4403577396","https://openalex.org/W7135042058","https://openalex.org/W4375957516","https://openalex.org/W2578396620","https://openalex.org/W4414668445","https://openalex.org/W4389519018"],"abstract_inverted_index":{"The":[0,177],"Differentiable":[1],"Search":[2],"Index":[3],"(DSI)":[4],"is":[5,96,111],"an":[6,45],"emerging":[7],"paradigm":[8],"for":[9,117,147],"information":[10],"retrieval.":[11,37],"Unlike":[12],"traditional":[13],"retrieval":[14,19,63,92,209,219],"architectures":[15],"where":[16,120],"index":[17],"and":[18,23,36,43,62,84,123,169,171,207,216],"are":[20,101,126],"two":[21],"different":[22,128],"separate":[24],"components,":[25],"DSI":[26,50,60,72,116,137,186,228],"uses":[27],"a":[28,141,157,165,174,190,194],"single":[29],"transformer":[30],"model":[31,168],"to":[32,75,188,193],"perform":[33],"both":[34],"indexing":[35,61,145,183,206],"In":[38],"this":[39,132],"paper,":[40],"we":[41,66,139],"identify":[42],"tackle":[44],"important":[46],"issue":[47],"of":[48,81,87,93,135,159,179,196],"current":[49,71,136],"models:":[51],"the":[52,59,79,85,88,106,185,205,208,226],"data":[53,200],"distribution":[54,201],"mismatch":[55],"that":[56,100,222],"occurs":[57],"between":[58,78,204],"processes.":[64],"Specifically,":[65],"argue":[67],"that,":[68],"at":[69,182],"indexing,":[70,152],"methods":[73],"learn":[74],"build":[76],"connections":[77],"text":[80,122,125],"long":[82],"documents":[83,155],"identifier":[86,192],"documents,":[89],"but":[90],"then":[91],"document":[94,121,191],"identifiers":[95],"based":[97],"on":[98,213],"queries":[99,162,181],"commonly":[102],"much":[103],"shorter":[104],"than":[105],"indexed":[107],"documents.":[108],"This":[109],"problem":[110,134],"further":[112],"exacerbated":[113],"when":[114],"using":[115],"cross-lingual":[118,217],"retrieval,":[119],"query":[124,166],"in":[127],"languages.":[129],"To":[130],"address":[131],"fundamental":[133],"models,":[138],"propose":[140],"simple":[142],"yet":[143],"effective":[144],"framework":[146],"DSI,":[148],"called":[149],"DSI-QG.":[150],"When":[151],"DSI-QG":[153,223],"represents":[154],"with":[156],"number":[158],"potentially":[160],"relevant":[161],"generated":[163],"by":[164,173],"generation":[167],"re-ranked":[170],"filtered":[172],"cross-encoder":[175],"ranker.":[176],"presence":[178],"these":[180],"allows":[184],"models":[187],"connect":[189],"set":[195],"queries,":[197],"hence":[198],"mitigating":[199],"mismatches":[202],"present":[203],"phases.":[210],"Empirical":[211],"results":[212],"popular":[214],"mono-lingual":[215],"passage":[218],"datasets":[220],"show":[221],"significantly":[224],"outperforms":[225],"original":[227],"model.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-06-24T00:00:00"}
