{"id":"https://openalex.org/W4384641088","doi":"https://doi.org/10.1145/3539618.3591916","title":"Reproducibility, Replicability, and Insights into Dense Multi-Representation Retrieval Models: from ColBERT to Col*","display_name":"Reproducibility, Replicability, and Insights into Dense Multi-Representation Retrieval Models: from ColBERT to Col*","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384641088","doi":"https://doi.org/10.1145/3539618.3591916"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591916","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/61958.html>,","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100411474","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0002-5151-2773"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057643560","display_name":"Craig Macdonald","orcid":"https://orcid.org/0000-0003-3143-279X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018894843","display_name":"Nicola Tonellotto","orcid":"https://orcid.org/0000-0002-7427-1001"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Tonellotto","raw_affiliation_strings":["University of Pisa, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079046603","display_name":"Iadh Ounis","orcid":"https://orcid.org/0000-0003-4701-3223"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iadh Ounis","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100411474"],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":1.0316,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80970937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2552","last_page":"2561"},"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":0.9993000030517578,"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":0.9961000084877014,"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":0.8141494989395142},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7611624598503113},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.7322450876235962},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.6299722194671631},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5872955322265625},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5352673530578613},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5349987745285034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5346111059188843},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5181987881660461},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.5019612312316895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49223223328590393},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4646425247192383},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4443349540233612},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4260188937187195},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08444538712501526},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0647607147693634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141494989395142},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7611624598503113},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7322450876235962},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.6299722194671631},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5872955322265625},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5352673530578613},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5349987745285034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5346111059188843},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5181987881660461},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5019612312316895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49223223328590393},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4646425247192383},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4443349540233612},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4260188937187195},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08444538712501526},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0647607147693634},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3539618.3591916","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:295749","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/61958.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:arpi.unipi.it:11568/1205607","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1205607","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:295749","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/61958.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2020622295","display_name":null,"funder_award_id":"Big Data","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2300736770","display_name":null,"funder_award_id":"(CSC)","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G4810374866","display_name":null,"funder_award_id":"China Scholarship Council","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320317295","display_name":"Dipartimenti di Eccellenza","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2121879602","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W3008374555","https://openalex.org/W3021397474","https://openalex.org/W3099700870","https://openalex.org/W3101140821","https://openalex.org/W3150521056","https://openalex.org/W3154670582","https://openalex.org/W3155895380","https://openalex.org/W3168875417","https://openalex.org/W3175987672","https://openalex.org/W3176692111","https://openalex.org/W3184918446","https://openalex.org/W4225492354","https://openalex.org/W4226112939","https://openalex.org/W4284674986","https://openalex.org/W4284699573","https://openalex.org/W4284712763","https://openalex.org/W4289516287","https://openalex.org/W4292433389","https://openalex.org/W4327644554","https://openalex.org/W6834284007"],"related_works":["https://openalex.org/W2912726924","https://openalex.org/W2564015900","https://openalex.org/W2963829519","https://openalex.org/W1995247875","https://openalex.org/W2380556669","https://openalex.org/W64465677","https://openalex.org/W2348055182","https://openalex.org/W4380789085","https://openalex.org/W4384641088","https://openalex.org/W2890190347"],"abstract_inverted_index":{"Dense":[0],"multi-representation":[1],"retrieval":[2,50,175],"models,":[3,90,163],"exemplified":[4],"as":[5,34,250],"ColBERT,":[6],"estimate":[7],"the":[8,18,62,82,94,108,113,125,145,149,155,167,182,192],"relevance":[9],"between":[10],"a":[11,14,253],"query":[12,188],"and":[13,48,110,133,164,171,190],"document":[15],"based":[16],"on":[17,93,174,186],"similarity":[19],"of":[20,81,112,136,157,169,184],"their":[21],"contextualised":[22,28,114],"token-level":[23],"embeddings.":[24],"Indeed,":[25],"by":[26,118],"using":[27],"token":[29,232],"embeddings,":[30],"dense":[31],"retrieval,":[32],"conducted":[33],"either":[35],"exact":[36,63],"or":[37],"semantic":[38,67,172,213,228,244],"matches,":[39],"can":[40,142],"result":[41],"in":[42,101,160,257],"increased":[43],"effectiveness":[44],"for":[45,86],"both":[46],"in-domain":[47],"out-of-domain":[49],"tasks,":[51],"indicating":[52],"that":[53,65],"it":[54],"is":[55,70,79],"an":[56],"important":[57,255],"model":[58],"to":[59,121,226],"study.":[60],"However,":[61],"role":[64,256],"these":[66],"matches":[68,158],"play":[69,252],"not":[71,98],"yet":[72],"well":[73],"investigated.":[74],"For":[75],"instance,":[76],"although":[77],"tokenisation":[78,140],"one":[80],"crucial":[83],"design":[84],"choices":[85],"various":[87,130,187],"pretrained":[88,131,198],"language":[89],"its":[91],"impact":[92,144],"matching":[95,146,173,214,229,242],"behaviour":[96,147,215],"has":[97],"been":[99],"examined":[100],"detail.":[102],"In":[103],"this":[104],"work,":[105],"we":[106,153],"inspect":[107],"reproducibility":[109],"replicability":[111],"late":[115,126,150,193,235,258],"interaction":[116,127,151,194,236],"mechanism":[117,128,195,237],"extending":[119],"ColBERT":[120,185],"Col\u22c6":[122,162],"which":[123],"implements":[124],"across":[129,217],"models":[132,199],"different":[134,139,161,197,201,218],"types":[135],"tokenisers.":[137,202],"As":[138],"methods":[141],"directly":[143],"within":[148],"mechanism,":[152],"study":[154],"nature":[156],"occurring":[159],"further":[165],"quantify":[166],"contribution":[168],"lexical":[170,241],"effectiveness.":[176],"Overall,":[177],"our":[178,204],"experiments":[179],"successfully":[180],"reproduce":[181],"performance":[183],"sets,":[189],"replicate":[191],"upon":[196],"with":[200],"Moreover,":[203],"experimental":[205],"results":[206],"yield":[207],"new":[208],"insights,":[209],"such":[210,249],"as:":[211],"(i)":[212],"varies":[216],"tokenisers;":[219],"(ii)":[220],"more":[221,239],"specifically,":[222],"high-frequency":[223],"tokens":[224],"tend":[225],"perform":[227],"than":[230,243],"other":[231],"families;":[233],"(iii)":[234],"benefits":[238],"from":[240],"matching;":[245],"(iv)":[246],"special":[247],"tokens,":[248],"[CLS],":[251],"very":[254],"interaction.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}