{"id":"https://openalex.org/W4306317500","doi":"https://doi.org/10.1145/3511808.3557588","title":"Early Stage Sparse Retrieval with Entity Linking","display_name":"Early Stage Sparse Retrieval with Entity Linking","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317500","doi":"https://doi.org/10.1145/3511808.3557588"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557588","pdf_url":null,"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":null,"license_id":null,"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":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074492035","display_name":"Dahlia Shehata","orcid":"https://orcid.org/0000-0002-7515-4069"},"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":true,"raw_author_name":"Dahlia Shehata","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049487742","display_name":"Negar Arabzadeh","orcid":"https://orcid.org/0000-0002-4411-7089"},"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":"Negar Arabzadeh","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037737168","display_name":"Charles L. A. Clarke","orcid":"https://orcid.org/0000-0001-8178-9194"},"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":"Charles L. A. Clarke","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074492035"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.8324,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.74481495,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4464","last_page":"4469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9986000061035156,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996399998664856,"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":0.8593461513519287},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6273795366287231},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4836934208869934},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.46766817569732666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4286603033542633},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41625869274139404},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4118499159812927},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.334102988243103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8593461513519287},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6273795366287231},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4836934208869934},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.46766817569732666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4286603033542633},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41625869274139404},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4118499159812927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.334102988243103},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557588","pdf_url":null,"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":null,"license_id":null,"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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1707562537","https://openalex.org/W1986968597","https://openalex.org/W1994500780","https://openalex.org/W2000431947","https://openalex.org/W2042980227","https://openalex.org/W2055629782","https://openalex.org/W2062270497","https://openalex.org/W2099421013","https://openalex.org/W2099868020","https://openalex.org/W2123142779","https://openalex.org/W2148972377","https://openalex.org/W2154610494","https://openalex.org/W2160825952","https://openalex.org/W2340462169","https://openalex.org/W2517031683","https://openalex.org/W2583976214","https://openalex.org/W2622338386","https://openalex.org/W2710956079","https://openalex.org/W2740321901","https://openalex.org/W2767929746","https://openalex.org/W2800576266","https://openalex.org/W2908332126","https://openalex.org/W2945303071","https://openalex.org/W2951534261","https://openalex.org/W3021397474","https://openalex.org/W3044284384","https://openalex.org/W3046493915","https://openalex.org/W3104616515","https://openalex.org/W3195010973","https://openalex.org/W3201233724","https://openalex.org/W3213719910","https://openalex.org/W4206827264","https://openalex.org/W4231856373","https://openalex.org/W4250467157"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2384605597","https://openalex.org/W4231274751","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1518215897","https://openalex.org/W1538046993"],"abstract_inverted_index":{"Despite":[0],"the":[1,22,25,41,60,101,115,123,126,135,159,163,171,187,197,240,243,264],"advantages":[2],"of":[3,20,59,78,103,117,205,222,266],"their":[4,68],"low-resource":[5],"settings,":[6],"traditional":[7],"sparse":[8,84,118,175],"retrievers":[9,46,64,119,178],"depend":[10],"on":[11,186],"exact":[12],"matching":[13],"approaches":[14],"between":[15,174],"high-dimensional":[16],"bag-of-words":[17],"(BoW)":[18],"representations":[19,58],"both":[21,122,247],"queries":[23,124],"and":[24,37,76,94,125,140,155,176,242,249],"collection.":[26],"As":[27],"a":[28,87,145,258],"result,":[29],"retrieval":[30,52,89,200,208],"performance":[31,116],"is":[32,219],"restricted":[33],"by":[34,54,120],"semantic":[35],"discrepancies":[36],"vocabulary":[38],"gaps.":[39],"On":[40],"other":[42],"hand,":[43],"transformer-based":[44],"dense":[45,63,104,148,177],"introduce":[47],"significant":[48],"improvements":[49],"in":[50,131,201,233],"information":[51,207],"tasks":[53],"exploiting":[55],"low-dimensional":[56],"contextualized":[57],"corpus.":[61,160],"While":[62],"are":[65,97,194],"known":[66],"for":[67,134,152,225],"relative":[69],"effectiveness,":[70],"they":[71],"suffer":[72],"from":[73],"lower":[74],"efficiency":[75],"lack":[77],"generalization":[79],"issues,":[80],"when":[81],"compared":[82],"to":[83,157,229,262],"retrievers.":[85],"For":[86],"lightweight":[88],"task,":[90],"high":[91],"computational":[92],"resources":[93],"time":[95],"consumption":[96],"major":[98],"barriers":[99],"encouraging":[100],"renunciation":[102],"models":[105],"despite":[106],"potential":[107],"gains.":[108],"In":[109],"this":[110],"work,":[111],"we":[112,168,193,210,256],"propose":[113],"boosting":[114],"expanding":[121],"documents":[127,224],"with":[128,196,246],"linked":[129],"entities":[130,251],"two":[132],"formats":[133],"entity":[136,149,153,165,267],"names:":[137],"1)":[138],"explicit":[139,248],"2)":[141],"hashed.":[142],"We":[143,182,236],"employ":[144],"zero-shot":[146],"end-to-end":[147],"linking":[150,166],"system":[151],"recognition":[154],"disambiguation":[156],"augment":[158],"By":[161],"leveraging":[162],"advanced":[164],"methods,":[167],"believe":[169],"that":[170,239],"effectiveness":[172],"gap":[173],"can":[179],"be":[180,230],"narrowed.":[181],"conduct":[183],"our":[184,212],"experiments":[185],"MS":[188],"MARCO":[189],"passage":[190],"dataset.":[191],"Since":[192],"concerned":[195],"early":[198],"stage":[199],"cascaded":[202],"ranking":[203],"architectures":[204],"large":[206],"systems,":[209],"evaluate":[211],"results":[213],"using":[214],"[email":[215],"protected]":[216],"Our":[217],"approach":[218,261],"also":[220],"capable":[221],"retrieving":[223],"query":[226],"subsets":[227],"judged":[228],"particularly":[231],"difficult":[232],"prior":[234],"work.":[235],"further":[237],"demonstrate":[238],"non-expanded":[241],"expanded":[244],"runs":[245],"hashed":[250],"retrieve":[252],"complementary":[253],"results.":[254],"Consequently,":[255],"adopt":[257],"run":[259],"fusion":[260],"maximize":[263],"benefits":[265],"linking.":[268]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-09T23:09:16.995542","created_date":"2025-10-10T00:00:00"}