{"id":"https://openalex.org/W4367047068","doi":"https://doi.org/10.1145/3543507.3583294","title":"LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval","display_name":"LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367047068","doi":"https://doi.org/10.1145/3543507.3583294"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583294","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","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/A5100324056","display_name":"Kai Zhang","orcid":"https://orcid.org/0000-0003-3850-5429"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai Zhang","raw_affiliation_strings":["The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073065834","display_name":"Chongyang Tao","orcid":"https://orcid.org/0000-0002-4162-2119"},"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":"Chongyang Tao","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611243","display_name":"Tao Shen","orcid":"https://orcid.org/0000-0003-3315-2468"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tao Shen","raw_affiliation_strings":["University of Technology Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071464274","display_name":"Can Xu","orcid":"https://orcid.org/0000-0002-1949-5715"},"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":"Can Xu","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084564357","display_name":"Xiubo Geng","orcid":"https://orcid.org/0000-0001-6477-7933"},"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":"Xiubo Geng","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045811313","display_name":"Binxing Jiao","orcid":"https://orcid.org/0000-0003-4710-0095"},"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":"Binxing Jiao","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060116992","display_name":"Daxin Jiang","orcid":"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":"Daxin Jiang","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100324056"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.1069,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79290325,"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":"3203","last_page":"3213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9922999739646912,"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/lexicon","display_name":"Lexicon","score":0.8061438798904419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6769753694534302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5448647737503052},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5386384129524231},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5348047018051147},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49227920174598694},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09115639328956604},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08853518962860107}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8061438798904419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769753694534302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5448647737503052},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5386384129524231},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5348047018051147},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49227920174598694},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09115639328956604},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08853518962860107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543507.3583294","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2108862644","https://openalex.org/W2143331230","https://openalex.org/W2610935556","https://openalex.org/W2997200074","https://openalex.org/W2998702515","https://openalex.org/W3021397474","https://openalex.org/W3036320503","https://openalex.org/W3098468692","https://openalex.org/W3154280800","https://openalex.org/W3154670582","https://openalex.org/W3154755316","https://openalex.org/W3155895380","https://openalex.org/W3156636935","https://openalex.org/W3156836409","https://openalex.org/W3157758108","https://openalex.org/W3170841641","https://openalex.org/W3172119680","https://openalex.org/W3174367567","https://openalex.org/W3184918446","https://openalex.org/W3198431451","https://openalex.org/W3206455169","https://openalex.org/W4206121183","https://openalex.org/W4225156005","https://openalex.org/W4225372933","https://openalex.org/W4226315795","https://openalex.org/W4252076394","https://openalex.org/W4281486957","https://openalex.org/W4283066191","https://openalex.org/W4288083766","https://openalex.org/W4289550880","https://openalex.org/W4297947729"],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W3195005284","https://openalex.org/W2391730868","https://openalex.org/W4394659737","https://openalex.org/W2759814045","https://openalex.org/W2118055728","https://openalex.org/W4399756845","https://openalex.org/W1831473261","https://openalex.org/W4293870971","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Retrieval":[0],"models":[1],"based":[2],"on":[3,116],"dense":[4,62,94,105,133],"representations":[5],"in":[6,23,43,50],"semantic":[7],"space":[8],"have":[9],"become":[10],"an":[11],"indispensable":[12],"branch":[13],"for":[14],"first-stage":[15,51],"retrieval.":[16,52],"These":[17],"retrievers":[18],"benefit":[19],"from":[20],"surging":[21],"advances":[22],"representation":[24,68],"learning":[25],"towards":[26],"compressive":[27],"global":[28],"sequence-level":[29],"embeddings.":[30],"However,":[31],"they":[32],"are":[33,154],"prone":[34],"to":[35,59,78,91,102,109],"overlook":[36],"local":[37],"salient":[38],"phrases":[39],"and":[40,96,138,141],"entity":[41],"mentions":[42],"texts,":[44],"which":[45,120,161],"usually":[46],"play":[47],"pivot":[48],"roles":[49],"To":[53],"mitigate":[54],"this":[55],"weakness,":[56],"we":[57,148],"propose":[58],"make":[60,103],"a":[61,65,87,98,124],"retriever":[63,81,127],"align":[64],"well-performing":[66],"lexicon-aware":[67,126,151],"model.":[69],"The":[70],"alignment":[71],"is":[72],"achieved":[73],"by":[74],"weakened":[75],"knowledge":[76],"distillations":[77],"enlighten":[79],"the":[80,93,104,110,129,157],"via":[82],"two":[83],"aspects":[84],"\u2013":[85],"1)":[86],"lexicon-augmented":[88],"contrastive":[89],"objective":[90],"challenge":[92],"encoder":[95],"2)":[97],"pair-wise":[99],"rank-consistent":[100],"regularization":[101],"model\u2019s":[106],"behavior":[107],"incline":[108],"other.":[111],"We":[112],"evaluate":[113],"our":[114,131,150],"model":[115],"three":[117],"public":[118],"benchmarks,":[119],"shows":[121],"that":[122],"with":[123,156],"comparable":[125],"as":[128],"teacher,":[130],"proposed":[132],"one":[134],"can":[135,162],"bring":[136],"consistent":[137],"significant":[139],"improvements,":[140],"even":[142],"outdo":[143],"its":[144],"teacher.":[145],"In":[146],"addition,":[147],"show":[149],"distillation":[152],"strategies":[153],"compatible":[155],"standard":[158],"ranker":[159],"distillation,":[160],"further":[163],"lift":[164],"state-of-the-art":[165],"performance.1":[166]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}