{"id":"https://openalex.org/W4306317003","doi":"https://doi.org/10.1145/3511808.3557367","title":"Introducing Neural Bag of Whole-Words with ColBERTer","display_name":"Introducing Neural Bag of Whole-Words with ColBERTer","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317003","doi":"https://doi.org/10.1145/3511808.3557367"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557367","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557367","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557367","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089466895","display_name":"Sebastian Hofst\u00e4tter","orcid":"https://orcid.org/0009-0006-1229-2612"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sebastian Hofst\u00e4tter","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","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, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005875282","display_name":"Sophia Althammer","orcid":"https://orcid.org/0000-0001-9134-3815"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sophia Althammer","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086407832","display_name":"Mete Sertkan","orcid":"https://orcid.org/0000-0003-0984-5221"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Mete Sertkan","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020665735","display_name":"Allan Hanbury","orcid":"https://orcid.org/0000-0002-7149-5843"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Allan Hanbury","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"737","last_page":"747"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9970999956130981,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7606323957443237},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7566653490066528},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7033877372741699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5605878829956055},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5577714443206787},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4259076416492462},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37865450978279114},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11399012804031372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606323957443237},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7566653490066528},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7033877372741699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5605878829956055},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5577714443206787},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4259076416492462},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37865450978279114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11399012804031372},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557367","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557367","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3511808.3557367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557367","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557367","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306317003.pdf","grobid_xml":"https://content.openalex.org/works/W4306317003.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2001142465","https://openalex.org/W2023217403","https://openalex.org/W2068098598","https://openalex.org/W2075893676","https://openalex.org/W2109244020","https://openalex.org/W2121879602","https://openalex.org/W2161701454","https://openalex.org/W2469056188","https://openalex.org/W2470818894","https://openalex.org/W2740492458","https://openalex.org/W2794432940","https://openalex.org/W2898078244","https://openalex.org/W2910883930","https://openalex.org/W2945806531","https://openalex.org/W3017330897","https://openalex.org/W3021397474","https://openalex.org/W3094476882","https://openalex.org/W3128581554","https://openalex.org/W3133594109","https://openalex.org/W3136473512","https://openalex.org/W3154670582","https://openalex.org/W3154755316","https://openalex.org/W3155480849","https://openalex.org/W3156166379","https://openalex.org/W3157758108","https://openalex.org/W3180230246","https://openalex.org/W3194741792","https://openalex.org/W3209791570","https://openalex.org/W3211670924","https://openalex.org/W4206390054","https://openalex.org/W4287201232"],"related_works":["https://openalex.org/W4385957992","https://openalex.org/W4229079080","https://openalex.org/W4206534706","https://openalex.org/W4385965371","https://openalex.org/W4200027074","https://openalex.org/W4386025632","https://openalex.org/W3006943036","https://openalex.org/W4200511449","https://openalex.org/W4211177414","https://openalex.org/W4299487748"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,10,147],"neural":[3,26],"information":[4],"retrieval":[5,27,181],"has":[6],"demonstrated":[7],"large":[8],"gains":[9,178],"quality,":[11],"while":[12,48,138],"often":[13],"sacrificing":[14],"efficiency":[15],"and":[16,66,90,94,124],"interpretability":[17,52],"compared":[18],"to":[19,92,102,112,136],"classical":[20],"approaches.":[21],"We":[22,105],"propose":[23],"ColBERTer,":[24],"a":[25],"model":[28],"using":[29,114],"contextualized":[30],"late":[31],"interaction":[32],"(ColBERT)":[33],"with":[34,156,160],"enhanced":[35],"reduction.":[36],"Along":[37],"the":[38,51,80,121,131,157],"effectiveness":[39,163],"Pareto":[40],"frontier,":[41],"ColBERTer":[42,60,78,129,151],"dramatically":[43],"lowers":[44],"ColBERT's":[45],"storage":[46,132,154],"requirements":[47],"simultaneously":[49],"improving":[50],"of":[53,82],"its":[54,75,148],"token-matching":[55],"scores.":[56],"To":[57],"this":[58],"end,":[59],"fuses":[61],"single-vector":[62],"retrieval,":[63],"multi-vector":[64,76],"refinement,":[65],"optional":[67],"lexical":[68],"matching":[69],"components":[70],"into":[71],"one":[72,143],"model.":[73],"For":[74],"component,":[77],"reduces":[79,130],"number":[81],"stored":[83],"vectors":[84],"by":[85,134],"learning":[86,91],"unique":[87],"whole-word":[88],"representations":[89,97],"identify":[93],"remove":[95],"word":[96],"that":[98,128],"are":[99],"not":[100],"essential":[101],"effective":[103],"scoring.":[104],"employ":[106],"an":[107],"explicit":[108],"multi-task,":[109],"multi-stage":[110],"training":[111],"facilitate":[113],"very":[115,161],"small":[116],"vector":[117],"dimensions.":[118],"Results":[119],"on":[120,170],"MS":[122],"MARCO":[123],"TREC-DL":[125],"collection":[126],"show":[127],"footprint":[133],"up":[135],"2.5x,":[137],"maintaining":[139],"effectiveness.":[140],"With":[141],"just":[142],"dimension":[144],"per":[145],"token":[146],"smallest":[149],"setting,":[150],"achieves":[152],"index":[153],"parity":[155],"plaintext":[158],"size,":[159],"strong":[162],"results.":[164],"Finally,":[165],"we":[166],"demonstrate":[167],"ColBERTer's":[168],"robustness":[169],"seven":[171],"high-quality":[172],"out-of-domain":[173],"collections,":[174],"yielding":[175],"statistically":[176],"significant":[177],"over":[179],"traditional":[180],"baselines.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}