{"id":"https://openalex.org/W3004203025","doi":"https://doi.org/10.1145/3366423.3380131","title":"Selective Weak Supervision for Neural Information Retrieval","display_name":"Selective Weak Supervision for Neural Information Retrieval","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3004203025","doi":"https://doi.org/10.1145/3366423.3380131","mag":"3004203025"},"language":"en","primary_location":{"id":"doi:10.1145/3366423.3380131","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380131","pdf_url":null,"source":null,"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 Web Conference 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3366423.3380131","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kaitao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaitao Zhang","raw_affiliation_strings":["Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenyan Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenyan Xiong","raw_affiliation_strings":["Carnegie Mellon University; Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University; Microsoft, USA","institution_ids":["https://openalex.org/I74973139","https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenghao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghao Liu","raw_affiliation_strings":["Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhiyuan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Liu","raw_affiliation_strings":["Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.1944,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89902849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"474","last_page":"485"},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9984999895095825,"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/T12676","display_name":"Machine Learning and ELM","score":0.9954000115394592,"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/learning-to-rank","display_name":"Learning to rank","score":0.7718999981880188},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7635999917984009},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7623000144958496},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6466000080108643},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.6263999938964844},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5430999994277954},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4339999854564667},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.7718999981880188},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7635999917984009},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7623000144958496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462999820709229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7125999927520752},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6466000080108643},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.6263999938964844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5817999839782715},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.40400001406669617},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26669999957084656},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3366423.3380131","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380131","pdf_url":null,"source":null,"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 Web Conference 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.10382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.10382","pdf_url":"https://arxiv.org/pdf/2001.10382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3366423.3380131","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380131","pdf_url":null,"source":null,"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 Web Conference 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2080825533","https://openalex.org/W2091808810","https://openalex.org/W2119717200","https://openalex.org/W2131876387","https://openalex.org/W2136189984","https://openalex.org/W2171161922","https://openalex.org/W2171710828","https://openalex.org/W2405884322","https://openalex.org/W2536015822","https://openalex.org/W2610935556","https://openalex.org/W2613589950","https://openalex.org/W2648699835","https://openalex.org/W2710956079","https://openalex.org/W2739916191","https://openalex.org/W2766284073","https://openalex.org/W2783640434","https://openalex.org/W2798598599","https://openalex.org/W2799037506","https://openalex.org/W2809897079","https://openalex.org/W2889658777","https://openalex.org/W2889757348","https://openalex.org/W2940927814","https://openalex.org/W2945127593","https://openalex.org/W2951434086","https://openalex.org/W2952841984","https://openalex.org/W2952866723","https://openalex.org/W2953774736","https://openalex.org/W2955732934","https://openalex.org/W2958100576","https://openalex.org/W2962739339","https://openalex.org/W2963157366","https://openalex.org/W2964012472","https://openalex.org/W2973132521","https://openalex.org/W4288280763","https://openalex.org/W4288616731"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"democratizes":[2],"neural":[3,49,79,96,112,135,159],"information":[4],"retrieval":[5],"to":[6,40,127,168],"scenarios":[7],"where":[8],"large":[9],"scale":[10],"relevance":[11,28,60,102],"training":[12],"signals":[13,152],"are":[14],"not":[15],"available.":[16],"We":[17],"revisit":[18],"the":[19,48,53,63,75,78,87,95,132,155,158],"classic":[20],"IR":[21],"intuition":[22],"that":[23,44,146],"anchor-document":[24,42,70,165],"relations":[25],"approximate":[26],"query-document":[27,169],"and":[29,85,130,162],"propose":[30],"a":[31,57,67],"reinforcement":[32],"weak":[33,150],"supervision":[34,151],"selection":[35,89],"method,":[36],"ReInfoSelect,":[37,116],"which":[38],"learns":[39],"select":[41],"pairs":[43,166],"best":[45],"weakly":[46],"supervise":[47],"ranker":[50,160],"(action),":[51],"using":[52,91],"ranking":[54],"performance":[55,98],"on":[56,100,108,154],"handful":[58],"of":[59,69,134,157],"labels":[61],"as":[62],"reward.":[64],"Iteratively,":[65],"for":[66],"batch":[68],"pairs,":[71],"ReInfoSelect":[72,147],"back":[73],"propagates":[74],"gradients":[76],"through":[77],"ranker,":[80],"gathers":[81],"its":[82],"NDCG":[83],"reward,":[84],"optimizes":[86],"data":[88],"network":[90],"policy":[92],"gradients,":[93],"until":[94],"ranker\u2019s":[97],"peaks":[99],"target":[101],"metrics":[103],"(convergence).":[104],"In":[105],"our":[106],"experiments":[107],"three":[109],"TREC":[110],"benchmarks,":[111],"rankers":[113,136],"trained":[114,137],"by":[115],"with":[117,138],"only":[118],"publicly":[119],"available":[120],"anchor":[121],"data,":[122],"significantly":[123],"outperform":[124],"feature-based":[125],"learning":[126],"rank":[128],"methods":[129],"match":[131],"effectiveness":[133],"private":[139],"commercial":[140],"search":[141],"logs.":[142],"Our":[143],"analyses":[144],"show":[145],"effectively":[148],"selects":[149],"based":[153],"stage":[156],"training,":[161],"intuitively":[163],"picks":[164],"similar":[167],"pairs.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2020-02-07T00:00:00"}