{"id":"https://openalex.org/W3021397474","doi":"https://doi.org/10.1145/3397271.3401075","title":"ColBERT","display_name":"ColBERT","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3021397474","doi":"https://doi.org/10.1145/3397271.3401075","mag":"3021397474"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401075","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd 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/A5015201177","display_name":"Omar Khattab","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Omar Khattab","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015201177"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":67.3281,"has_fulltext":false,"cited_by_count":1001,"citation_normalized_percentile":{"value":0.99935445,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.8699951767921448},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6649989485740662},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6466085910797119},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6014922857284546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5154420137405396},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4753658175468445},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45435819029808044},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.43893831968307495},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.42705437541007996},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4211776852607727},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3694239556789398},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.07919898629188538}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8699951767921448},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6649989485740662},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6466085910797119},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6014922857284546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5154420137405396},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4753658175468445},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45435819029808044},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.43893831968307495},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.42705437541007996},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4211776852607727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3694239556789398},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.07919898629188538},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397271.3401075","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W2112508839","https://openalex.org/W2136189984","https://openalex.org/W2536015822","https://openalex.org/W2539671052","https://openalex.org/W2648699835","https://openalex.org/W2725049817","https://openalex.org/W2783640434","https://openalex.org/W2886950694","https://openalex.org/W2887729785","https://openalex.org/W2897754576","https://openalex.org/W2899154813","https://openalex.org/W2940927814","https://openalex.org/W2945806531","https://openalex.org/W2951534261","https://openalex.org/W2953774736","https://openalex.org/W2963403868","https://openalex.org/W2970565456","https://openalex.org/W2971209824","https://openalex.org/W3102286003","https://openalex.org/W3104055892","https://openalex.org/W4206655182"],"related_works":["https://openalex.org/W3127142483","https://openalex.org/W3092292339","https://openalex.org/W4385565564","https://openalex.org/W2898073868","https://openalex.org/W4390446658","https://openalex.org/W2138488530","https://openalex.org/W2971071571","https://openalex.org/W2798835721","https://openalex.org/W2922169395","https://openalex.org/W2387658907"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,11],"Natural":[3],"Language":[4],"Understanding":[5],"(NLU)":[6],"is":[7,178],"driving":[8],"fast-paced":[9],"advances":[10],"Information":[12],"Retrieval":[13],"(IR),":[14],"largely":[15],"owed":[16],"to":[17,59,136,197],"fine-tuning":[18],"deep":[19,77,129],"language":[20],"models":[21,31,111,183],"(LMs)":[22],"for":[23,82,155],"document":[24,98,138],"ranking.":[25],"While":[26],"remarkably":[27],"effective,":[28],"the":[29,94,97,126,134],"ranking":[30,73],"based":[32],"on":[33],"these":[34],"LMs":[35,78,130],"increase":[36],"computational":[37],"cost":[38],"by":[39],"orders":[40],"of":[41,128,161],"magnitude":[42],"over":[43],"prior":[44],"approaches,":[45],"particularly":[46],"as":[47],"they":[48],"must":[49],"feed":[50],"each":[51],"query-document":[52],"pair":[53],"through":[54],"a":[55,61,71,87,104],"massive":[56],"neural":[57],"network":[58],"compute":[60],"single":[62],"relevance":[63],"score.":[64],"To":[65],"tackle":[66],"this,":[67],"we":[68],"present":[69],"ColBERT,":[70],"novel":[72],"model":[74],"that":[75,91,110,175],"adapts":[76],"(in":[79],"particular,":[80],"BERT)":[81],"efficient":[83],"retrieval.":[84],"ColBERT":[85,123,166],"introduces":[86],"late":[88],"interaction":[89,108,149],"architecture":[90],"independently":[92],"encodes":[93],"query":[95,144],"and":[96,101,117,194],"using":[99,167],"BERT":[100],"then":[102],"employs":[103],"cheap":[105],"yet":[106,118],"powerful":[107],"step":[109],"their":[112],"fine-grained":[113],"similarity.":[114],"By":[115],"delaying":[116],"retaining":[119],"this":[120],"fine-granular":[121],"interaction,":[122],"can":[124],"leverage":[125],"expressiveness":[127],"while":[131,189],"simultaneously":[132],"gaining":[133],"ability":[135],"pre-compute":[137],"representations":[139],"offline,":[140],"considerably":[141],"speeding":[142],"up":[143,196],"processing.":[145],"Crucially,":[146],"ColBERT's":[147,176],"pruning-friendly":[148],"mechanism":[150],"enables":[151],"leveraging":[152],"vector-similarity":[153],"indexes":[154],"end-to-end":[156],"retrieval":[157],"directly":[158],"from":[159],"millions":[160],"documents.":[162],"We":[163],"extensively":[164],"evaluate":[165],"two":[168,191],"recent":[169],"passage":[170],"search":[171],"datasets.":[172],"Results":[173],"show":[174],"effectiveness":[177],"competitive":[179],"with":[180],"existing":[181],"BERT-based":[182],"(and":[184],"outperforms":[185],"every":[186],"non-BERT":[187],"baseline),":[188],"executing":[190],"orders-of-magnitude":[192,199],"faster":[193],"requiring":[195],"four":[198],"fewer":[200],"FLOPs":[201],"per":[202],"query.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":49},{"year":2025,"cited_by_count":269},{"year":2024,"cited_by_count":195},{"year":2023,"cited_by_count":183},{"year":2022,"cited_by_count":137},{"year":2021,"cited_by_count":149},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2020-05-13T00:00:00"}