{"id":"https://openalex.org/W4388955793","doi":"https://doi.org/10.1145/3624918.3625334","title":"Enhancing Sparse Retrieval via Unsupervised Learning","display_name":"Enhancing Sparse Retrieval via Unsupervised Learning","publication_year":2023,"publication_date":"2023-11-23","ids":{"openalex":"https://openalex.org/W4388955793","doi":"https://doi.org/10.1145/3624918.3625334"},"language":"en","primary_location":{"id":"doi:10.1145/3624918.3625334","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624918.3625334","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624918.3625334","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624918.3625334","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021623012","display_name":"Xueguang Ma","orcid":"https://orcid.org/0000-0003-3430-4910"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xueguang Ma","raw_affiliation_strings":["University of Waterloo, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3430-4910","affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084148879","display_name":"Hengxin Fun","orcid":"https://orcid.org/0009-0009-0157-0017"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hengxin Fun","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":"https://orcid.org/0009-0009-0157-0017","affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080354317","display_name":"Xusen Yin","orcid":"https://orcid.org/0009-0000-8170-6934"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xusen Yin","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":"https://orcid.org/0009-0000-8170-6934","affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004258130","display_name":"Antonio Mallia","orcid":"https://orcid.org/0000-0002-7817-6140"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Mallia","raw_affiliation_strings":["Amazon Alexa AI, USA"],"raw_orcid":"https://orcid.org/0000-0002-7817-6140","affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0661-7189","affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8691,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76086538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"150","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9984999895095825,"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":0.8332195281982422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7282254099845886},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6172285079956055},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5200840830802917},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5114456415176392},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5008382797241211},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.47714897990226746},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3718189001083374},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32332104444503784},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.258273720741272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332195281982422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7282254099845886},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6172285079956055},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5200840830802917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5114456415176392},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5008382797241211},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.47714897990226746},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3718189001083374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32332104444503784},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.258273720741272},{"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:10.1145/3624918.3625334","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624918.3625334","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624918.3625334","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3624918.3625334","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624918.3625334","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624918.3625334","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388955793.pdf","grobid_xml":"https://content.openalex.org/works/W4388955793.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2740321901","https://openalex.org/W2892181857","https://openalex.org/W2912924812","https://openalex.org/W2951434086","https://openalex.org/W2962985038","https://openalex.org/W2963339397","https://openalex.org/W2998702515","https://openalex.org/W3034912391","https://openalex.org/W3035390927","https://openalex.org/W3035524453","https://openalex.org/W3099700870","https://openalex.org/W3154755316","https://openalex.org/W3168875417","https://openalex.org/W3180230246","https://openalex.org/W3184918446","https://openalex.org/W3185250692","https://openalex.org/W3208821253","https://openalex.org/W4252076394","https://openalex.org/W4284682639","https://openalex.org/W4384823501"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2150136235","https://openalex.org/W2053591227","https://openalex.org/W2581240705","https://openalex.org/W2041353081","https://openalex.org/W2568183987","https://openalex.org/W2806873178","https://openalex.org/W2770818364","https://openalex.org/W2965146396","https://openalex.org/W4312416532"],"abstract_inverted_index":{"Recent":[0],"work":[1],"has":[2,50],"shown":[3],"that":[4,38,99,143],"neural":[5],"retrieval":[6,36,56,64,171],"models":[7,37,57,65,155],"excel":[8],"at":[9],"text":[10],"ranking":[11],"tasks":[12],"in":[13,53,81,167],"a":[14,59],"supervised":[15,153],"setting":[16],"when":[17],"given":[18],"large":[19],"amounts":[20],"of":[21],"manually":[22],"labeled":[23],"training":[24],"data.":[25],"However,":[26],"it":[27],"remains":[28],"an":[29,82,138],"open":[30],"question":[31],"how":[32],"to":[33,71,121,136],"train":[34],"unsupervised":[35,54,62,83,112,139],"are":[39],"more":[40],"effective":[41],"than":[42],"baselines":[43],"such":[44,76,156],"as":[45,157],"BM25.":[46],"While":[47],"some":[48],"progress":[49],"been":[51],"made":[52],"dense":[55,113],"within":[58],"bi-encoder":[60],"architecture,":[61],"sparse":[63,154],"remain":[66],"unexplored.":[67],"We":[68,115],"propose":[69],"BM26,":[70,163],"our":[72],"knowledge":[73],"the":[74,86,109],"first":[75],"model,":[77],"which":[78],"is":[79],"trained":[80],"manner":[84],"without":[85],"need":[87],"for":[88],"any":[89],"human":[90],"relevance":[91],"judgments.":[92],"Evaluations":[93],"with":[94,104,159],"multiple":[95],"test":[96],"collections":[97],"show":[98],"BM26":[100,131],"performs":[101],"on":[102],"par":[103],"BM25":[105,129,147],"and":[106,130,169],"outperforms":[107],"Contriever,":[108],"current":[110],"state-of-the-art":[111],"retriever.":[114],"further":[116],"demonstrate":[117],"two":[118],"promising":[119],"avenues":[120],"enhance":[122,152],"lexical":[123],"retrieval:":[124],"First,":[125],"we":[126,150],"can":[127,151],"combine":[128],"using":[132,162],"simple":[133],"vector":[134],"concatenation":[135],"yield":[137],"hybrid":[140],"BM51":[141],"model":[142],"significantly":[144],"improves":[145],"over":[146],"alone.":[148],"Second,":[149],"SPLADE":[158],"improved":[160],"initialization":[161],"yielding":[164],"significant":[165],"improvements":[166],"in-domain":[168],"zero-shot":[170],"effectiveness.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}