{"id":"https://openalex.org/W3038831159","doi":"https://doi.org/10.1162/tacl_a_00405","title":"Relevance-guided Supervision for OpenQA with ColBERT","display_name":"Relevance-guided Supervision for OpenQA with ColBERT","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3038831159","doi":"https://doi.org/10.1162/tacl_a_00405","mag":"3038831159"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00405","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00405","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00405/1962458/tacl_a_00405.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00405/1962458/tacl_a_00405.pdf","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Omar Khattab","raw_affiliation_strings":["Stanford University, United States. okhattab@stanford.edu","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, United States. okhattab@stanford.edu","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042601761","display_name":"Christopher Potts","orcid":"https://orcid.org/0000-0002-7978-6055"},"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":"Christopher Potts","raw_affiliation_strings":["Stanford University, United States. cgpotts@stanford.edu","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, United States. cgpotts@stanford.edu","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","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, United States. matei@cs.stanford.edu","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, United States. matei@cs.stanford.edu","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.9498,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87966896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"929","last_page":"944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.7296475172042847},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6493408679962158},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6115365028381348},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5354850888252258},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.531265914440155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4815364480018616},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4490014314651489},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.42972898483276367},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35839012265205383},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32246536016464233},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11411142349243164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7296475172042847},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6493408679962158},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6115365028381348},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5354850888252258},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.531265914440155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4815364480018616},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4490014314651489},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.42972898483276367},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35839012265205383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32246536016464233},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11411142349243164},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1162/tacl_a_00405","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00405","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00405/1962458/tacl_a_00405.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2007.00814","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.00814","pdf_url":"https://arxiv.org/pdf/2007.00814","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:3038831159","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.00814","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:doaj.org/article:c91fdb9d327e4cffbc8ad63cdf99fa87","is_oa":true,"landing_page_url":"https://doaj.org/article/c91fdb9d327e4cffbc8ad63cdf99fa87","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 9, Pp 929-944 (2021)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2007.00814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.00814","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.57702/1c44xsal","is_oa":true,"landing_page_url":"https://doi.org/10.57702/1c44xsal","pdf_url":null,"source":{"id":"https://openalex.org/S7407053387","display_name":"TIB Data Manager","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00405","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00405","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00405/1962458/tacl_a_00405.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1861310076","display_name":null,"funder_award_id":"CNS-1651570","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320316785","display_name":"VMware","ror":null},{"id":"https://openalex.org/F4320330001","display_name":"Ant Financial Services Group","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3038831159.pdf","grobid_xml":"https://content.openalex.org/works/W3038831159.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W2028175314","https://openalex.org/W2121300346","https://openalex.org/W2130237711","https://openalex.org/W2155482025","https://openalex.org/W2171278097","https://openalex.org/W2251349042","https://openalex.org/W2251818205","https://openalex.org/W2252136820","https://openalex.org/W2361488420","https://openalex.org/W2558203065","https://openalex.org/W2610935556","https://openalex.org/W2899154813","https://openalex.org/W2912817604","https://openalex.org/W2912924812","https://openalex.org/W2951434086","https://openalex.org/W2955732934","https://openalex.org/W2962865973","https://openalex.org/W2962985038","https://openalex.org/W2963339397","https://openalex.org/W2963403868","https://openalex.org/W2963748441","https://openalex.org/W2970168256","https://openalex.org/W2971105107","https://openalex.org/W2971209824","https://openalex.org/W2979826702","https://openalex.org/W2989312920","https://openalex.org/W2995638926","https://openalex.org/W2998702515","https://openalex.org/W3004203025","https://openalex.org/W3021397474","https://openalex.org/W3034671305","https://openalex.org/W3034999214","https://openalex.org/W3098417575","https://openalex.org/W3098824823","https://openalex.org/W3099700870","https://openalex.org/W6628905179","https://openalex.org/W6678890848","https://openalex.org/W6691476020","https://openalex.org/W6729938257","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6767405490","https://openalex.org/W6770413283","https://openalex.org/W6770949304","https://openalex.org/W6777615688","https://openalex.org/W6779857854"],"related_works":["https://openalex.org/W2912924812","https://openalex.org/W2963339397","https://openalex.org/W2951434086","https://openalex.org/W3199493219","https://openalex.org/W2963341956","https://openalex.org/W3099700870","https://openalex.org/W3082274269","https://openalex.org/W3027879771","https://openalex.org/W2971105107","https://openalex.org/W3102659883","https://openalex.org/W3039017601","https://openalex.org/W2963748441","https://openalex.org/W2963403868","https://openalex.org/W2962718483","https://openalex.org/W3007672467","https://openalex.org/W2995638926","https://openalex.org/W2912817604","https://openalex.org/W2989312920","https://openalex.org/W2965373594","https://openalex.org/W2970971581"],"abstract_inverted_index":{"Abstract":[0],"Systems":[1],"for":[2,12,23,57],"Open-Domain":[3],"Question":[4],"Answering":[5],"(OpenQA)":[6],"generally":[7],"depend":[8],"on":[9,112,127],"a":[10,17,21,36],"retriever":[11,34],"finding":[13],"candidate":[14],"passages":[15],"in":[16],"large":[18],"corpus":[19],"and":[20,46,88,116,118],"reader":[22],"extracting":[24],"answers":[25],"from":[26],"those":[27],"passages.":[28,47,89],"In":[29],"much":[30],"recent":[31],"work,":[32],"the":[33,60,74,119],"is":[35,54],"learned":[37],"component":[38],"that":[39,50,97],"uses":[40,99],"coarse-grained":[41],"vector":[42],"representations":[43],"of":[44,62],"questions":[45,87],"We":[48,90],"argue":[49],"this":[51],"modeling":[52],"choice":[53],"insufficiently":[55],"expressive":[56],"dealing":[58],"with":[59],"complexity":[61],"natural":[63],"language":[64],"questions.":[65],"To":[66],"address":[67],"this,":[68],"we":[69],"define":[70],"ColBERT-QA,":[71],"which":[72],"adapts":[73],"scalable":[75],"neural":[76],"retrieval":[77,111],"model":[78],"ColBERT":[79,82,100],"to":[80,101],"OpenQA.":[81],"creates":[83],"fine-grained":[84],"interactions":[85],"between":[86],"propose":[91],"an":[92],"efficient":[93],"weak":[94],"supervision":[95],"strategy":[96],"iteratively":[98],"create":[102],"its":[103],"own":[104],"training":[105],"data.":[106],"This":[107],"greatly":[108],"improves":[109],"OpenQA":[110,125],"Natural":[113],"Questions,":[114],"SQuAD,":[115],"TriviaQA,":[117],"resulting":[120],"system":[121],"attains":[122],"state-of-the-art":[123],"extractive":[124],"performance":[126],"all":[128],"three":[129],"datasets.":[130]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2020-07-10T00:00:00"}