{"id":"https://openalex.org/W4391680357","doi":"https://doi.org/10.1145/3640460","title":"Revisiting Bag of Words Document Representations for Efficient Ranking with Transformers","display_name":"Revisiting Bag of Words Document Representations for Efficient Ranking with Transformers","publication_year":2024,"publication_date":"2024-02-09","ids":{"openalex":"https://openalex.org/W4391680357","doi":"https://doi.org/10.1145/3640460"},"language":"en","primary_location":{"id":"doi:10.1145/3640460","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640460","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640460","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3640460","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075484241","display_name":"David Rau","orcid":"https://orcid.org/0000-0002-1964-1356"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"David Rau","raw_affiliation_strings":["ILLC, University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-1964-1356","affiliations":[{"raw_affiliation_string":"ILLC, University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102906366","display_name":"Mostafa Dehghani","orcid":"https://orcid.org/0000-0002-9772-1095"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mostafa Dehghani","raw_affiliation_strings":["Deep Mind, San Francisco, United States"],"raw_orcid":"https://orcid.org/0000-0002-9772-1095","affiliations":[{"raw_affiliation_string":"Deep Mind, San Francisco, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044511901","display_name":"Jaap Kamps","orcid":"https://orcid.org/0000-0002-6614-0087"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jaap Kamps","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-6614-0087","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6311,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84775743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"42","issue":"5","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9950000047683716,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.989799976348877,"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":0.791521430015564},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7260700464248657},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6990018486976624},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5748255252838135},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5329058766365051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46936944127082825},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4561258554458618},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4076244533061981},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3515234589576721},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34801042079925537},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09046351909637451}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791521430015564},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7260700464248657},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6990018486976624},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5748255252838135},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5329058766365051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46936944127082825},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4561258554458618},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4076244533061981},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3515234589576721},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34801042079925537},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09046351909637451},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3640460","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640460","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640460","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:openaire/433a094a-a9ea-4048-9c26-6825efbbb3e6","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/revisiting-bag-of-words-document-representations-for-efficient-ranking-with-transformers(433a094a-a9ea-4048-9c26-6825efbbb3e6).html","pdf_url":"https://pure.uva.nl/ws/files/195549194/3640460-1.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Rau, D, Dehghani, M & Kamps, J 2024, 'Revisiting Bag of Words Document Representations for Efficient Ranking with Transformers', ACM Transactions on Information Systems, vol. 42, no. 5, 114. https://doi.org/10.1145/3640460","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3640460","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640460","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640460","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4723783796","display_name":"Access to City Councils using Exploratory Search Systems (ACCESS)","funder_award_id":"CISC.CC.016","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320313716","display_name":"Canadian Institute of Steel Construction","ror":"https://ror.org/04w9bz196"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391680357.pdf","grobid_xml":"https://content.openalex.org/works/W4391680357.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1522301498","https://openalex.org/W1973289172","https://openalex.org/W1974339500","https://openalex.org/W2043909051","https://openalex.org/W2099654552","https://openalex.org/W2104978738","https://openalex.org/W2136189984","https://openalex.org/W2144211451","https://openalex.org/W2169583766","https://openalex.org/W2511076825","https://openalex.org/W2536345451","https://openalex.org/W2610935556","https://openalex.org/W2648699835","https://openalex.org/W2740321901","https://openalex.org/W2897754576","https://openalex.org/W2911109671","https://openalex.org/W2945127593","https://openalex.org/W2953774736","https://openalex.org/W2955375559","https://openalex.org/W2964110616","https://openalex.org/W2970971581","https://openalex.org/W2980282514","https://openalex.org/W3015468748","https://openalex.org/W3021397474","https://openalex.org/W3021779606","https://openalex.org/W3022978951","https://openalex.org/W3033529678","https://openalex.org/W3034506277","https://openalex.org/W3034912391","https://openalex.org/W3085139254","https://openalex.org/W3093955333","https://openalex.org/W3098965860","https://openalex.org/W3099384026","https://openalex.org/W3099446234","https://openalex.org/W3100107515","https://openalex.org/W3103682594","https://openalex.org/W3104220682","https://openalex.org/W3123856867","https://openalex.org/W3131922516","https://openalex.org/W3140853032","https://openalex.org/W3156413894","https://openalex.org/W3156830884","https://openalex.org/W3172119680","https://openalex.org/W3174169056","https://openalex.org/W4252076394","https://openalex.org/W4284664419","https://openalex.org/W4287375343","https://openalex.org/W4287779273","https://openalex.org/W4288350560","https://openalex.org/W4293248701","https://openalex.org/W4295312788","https://openalex.org/W4295838474","https://openalex.org/W4297745984","https://openalex.org/W4323654151","https://openalex.org/W4378513414","https://openalex.org/W4387596624","https://openalex.org/W6761628794","https://openalex.org/W6763355497","https://openalex.org/W6771626834","https://openalex.org/W6776048684","https://openalex.org/W6779163297","https://openalex.org/W6785783668"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W4381058564","https://openalex.org/W3003945460","https://openalex.org/W2964413124","https://openalex.org/W4288267738","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Modern":[0],"transformer-based":[1],"information":[2],"retrieval":[3,88,98],"models":[4,16,85,146,150],"achieve":[5],"state-of-the-art":[6],"performance":[7],"across":[8],"various":[9,84],"benchmarks.":[10],"The":[11],"self-attention":[12],"of":[13,42,56,68,141],"the":[14,25,45,78,118,157],"transformer":[15],"is":[17],"a":[18,66,124],"powerful":[19],"mechanism":[20],"to":[21,48,74,155],"contextualize":[22],"terms":[23],"over":[24],"whole":[26],"input":[27,35,79],"but":[28,161,168],"quickly":[29],"becomes":[30],"prohibitively":[31],"expensive":[32],"for":[33,86,128],"long":[34],"as":[36,93,95],"required":[37],"in":[38,105,123],"document":[39,58,87,97],"retrieval.":[40],"Instead":[41],"focusing":[43],"on":[44,89,99],"model":[46],"itself":[47],"improve":[49],"efficiency,":[50],"this":[51,139],"paper":[52],"explores":[53],"different":[54],"bag":[55],"words":[57],"representations":[59],"that":[60],"encode":[61],"full":[62],"documents":[63],"by":[64],"only":[65],"fraction":[67],"their":[69],"characteristic":[70],"terms,":[71],"allowing":[72,127],"us":[73],"control":[75],"and":[76,101,120,134,151,166],"reduce":[77],"length.":[80],"We":[81],"experiment":[82],"with":[83,147],"MS":[90],"MARCO":[91],"data,":[92],"well":[94],"zero-shot":[96],"Robust04,":[100],"show":[102],"large":[103],"gains":[104,114],"efficiency":[106,113],"while":[107],"retaining":[108],"reasonable":[109],"effectiveness.":[110],"Inference":[111],"time":[112,119],"are":[115],"both":[116],"lowering":[117],"memory":[121,132],"complexity":[122],"controllable":[125],"way,":[126],"further":[129],"trading":[130],"off":[131],"footprint":[133],"query":[135],"latency.":[136],"More":[137],"generally,":[138],"line":[140],"research":[142],"connects":[143],"traditional":[144,164],"IR":[145],"neural":[148,171],"\u201cNLP\u201d":[149],"offers":[152],"novel":[153],"ways":[154],"explore":[156],"space":[158],"between":[159],"(efficient,":[160],"less":[162,169],"effective)":[163],"rankers":[165,172],"(effective,":[167],"efficient)":[170],"elegantly.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-10T00:00:00"}