{"id":"https://openalex.org/W2889757348","doi":"https://doi.org/10.1145/3234944.3234968","title":"On the Theory of Weak Supervision for Information Retrieval","display_name":"On the Theory of Weak Supervision for Information Retrieval","publication_year":2018,"publication_date":"2018-09-10","ids":{"openalex":"https://openalex.org/W2889757348","doi":"https://doi.org/10.1145/3234944.3234968","mag":"2889757348"},"language":"en","primary_location":{"id":"doi:10.1145/3234944.3234968","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3234944.3234968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101457713","display_name":"Hamed Zamani","orcid":"https://orcid.org/0000-0002-0800-3340"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Zamani","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105659698","display_name":"W. Bruce Croft","orcid":"https://orcid.org/0000-0003-2391-9629"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Bruce Croft","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},{"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"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9955999851226807,"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":0.7280649542808533},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.6820192337036133},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6543067097663879},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5624975562095642},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5604445934295654},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5583707094192505},{"id":"https://openalex.org/keywords/empirical-risk-minimization","display_name":"Empirical risk minimization","score":0.530670702457428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4921080470085144},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48636606335639954},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4828675091266632},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4313107132911682},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4180557131767273},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32399600744247437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1631338894367218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7280649542808533},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6820192337036133},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6543067097663879},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5624975562095642},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5604445934295654},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5583707094192505},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.530670702457428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4921080470085144},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48636606335639954},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4828675091266632},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4313107132911682},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4180557131767273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32399600744247437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1631338894367218},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3234944.3234968","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3234944.3234968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1685426458","https://openalex.org/W1926592634","https://openalex.org/W1975128126","https://openalex.org/W1982858363","https://openalex.org/W1992113527","https://openalex.org/W2047221353","https://openalex.org/W2048679005","https://openalex.org/W2093390569","https://openalex.org/W2102046030","https://openalex.org/W2122052811","https://openalex.org/W2136542423","https://openalex.org/W2148212498","https://openalex.org/W2153579005","https://openalex.org/W2159665776","https://openalex.org/W2159981039","https://openalex.org/W2169213601","https://openalex.org/W2250539671","https://openalex.org/W2403681572","https://openalex.org/W2507134384","https://openalex.org/W2536015822","https://openalex.org/W2604436559","https://openalex.org/W2610935556","https://openalex.org/W2613589950","https://openalex.org/W2618574054","https://openalex.org/W2648699835","https://openalex.org/W2765482949","https://openalex.org/W2772357980","https://openalex.org/W2792379413","https://openalex.org/W2798483934","https://openalex.org/W2798631888","https://openalex.org/W2809897079","https://openalex.org/W2810410758","https://openalex.org/W2963386594","https://openalex.org/W2963697299","https://openalex.org/W2964121744","https://openalex.org/W3102839128","https://openalex.org/W3212575067","https://openalex.org/W4206765718","https://openalex.org/W4240913316","https://openalex.org/W4246858749","https://openalex.org/W4297944103"],"related_works":["https://openalex.org/W2011472225","https://openalex.org/W3000057026","https://openalex.org/W3048565508","https://openalex.org/W3163984363","https://openalex.org/W3127142483","https://openalex.org/W2119384858","https://openalex.org/W4385565564","https://openalex.org/W2898073868","https://openalex.org/W2138488530","https://openalex.org/W4390446658"],"abstract_inverted_index":{"Neural":[0],"network":[1],"approaches":[2,17],"have":[3,113],"recently":[4,49],"shown":[5,91],"to":[6,25,148,163,188,222,242],"be":[7],"effective":[8],"in":[9,55,92,117,207],"several":[10],"information":[11,143,230],"retrieval":[12],"(IR)":[13],"tasks.":[14],"However,":[15],"neural":[16,41,98],"often":[18],"require":[19],"large":[20,69],"volumes":[21],"of":[22,37,71,204,209,237,257],"training":[23,40],"data":[24],"perform":[26],"effectively,":[27],"which":[28],"is":[29,79,186],"not":[30],"always":[31],"available.":[32],"To":[33],"mitigate":[34],"the":[35,56,83,96,102,120,127,152,164,169,181,201,213,235,248],"shortage":[36],"labeled":[38],"data,":[39,73],"IR":[42],"models":[43],"with":[44],"weak":[45,59,103,140,153,184,205,219,238,265],"supervision":[46,141,154,185,206,220,239,266],"has":[47,89],"been":[48,90,114],"proposed":[50],"and":[51,74,263],"received":[52],"considerable":[53],"attention":[54],"literature.":[57],"In":[58,131],"supervision,":[60],"an":[61,197,229,244],"existing":[62],"model":[63,78,99,151],"automatically":[64],"generates":[65],"labels":[66],"for":[67,126,142,200,247],"a":[68,75,106,136,157,255],"set":[70,256],"unlabeled":[72],"machine":[76],"learning":[77,147,190],"further":[80],"trained":[81,97],"on":[82,146,168,180,216,234],"generated":[84],"\"weak\"":[85],"data.":[86,267],"Surprisingly,":[87],"it":[88],"prior":[93],"art":[94],"that":[95,160,175],"can":[100],"outperform":[101],"labeler":[104],"by":[105],"significant":[107],"margin.":[108],"Although":[109],"these":[110],"obtained":[111],"improvements":[112],"intuitively":[115],"justified":[116],"previous":[118],"work,":[119],"literature":[121],"still":[122],"lacks":[123],"theoretical":[124,137,259],"justification":[125],"observed":[128],"empirical":[129,202],"findings.":[130],"this":[132],"paper,":[133],"we":[134,173,227],"provide":[135],"insight":[138],"into":[139],"retrieval,":[144],"focusing":[145],"rank.":[149],"We":[150,194,252],"signal":[155],"as":[156],"noisy":[158],"channel":[159],"introduces":[161],"noise":[162],"correct":[165],"ranking.":[166],"Based":[167],"risk":[170,203],"minimization":[171],"framework,":[172],"prove":[174],"given":[176],"some":[177],"sufficient":[178],"constraints":[179],"loss":[182],"function,":[183],"equivalent":[187],"supervised":[189],"under":[191],"uniform":[192],"noise.":[193,211],"also":[195],"find":[196,228],"upper":[198,245],"bound":[199,233,246],"case":[208],"non-uniform":[210],"Following":[212],"recent":[214],"work":[215],"using":[217,261],"multiple":[218],"signals":[221,240],"learn":[223],"more":[224],"accurate":[225],"models,":[226],"theoretic":[231],"lower":[232],"number":[236],"required":[241],"guarantee":[243],"pairwise":[249],"error":[250],"probability.":[251],"empirically":[253],"verify":[254],"presented":[258],"findings,":[260],"synthetic":[262],"real":[264]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}