{"id":"https://openalex.org/W4306316937","doi":"https://doi.org/10.1145/3511808.3557582","title":"Discriminative Language Model via Self-Teaching for Dense Retrieval","display_name":"Discriminative Language Model via Self-Teaching for Dense Retrieval","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306316937","doi":"https://doi.org/10.1145/3511808.3557582"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557582","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557582","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557582","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100432087","display_name":"Lu Chen","orcid":"https://orcid.org/0000-0002-4577-1736"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Chen","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, ICT, CAS; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, ICT, CAS; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009898523","display_name":"Ruqing Zhang","orcid":"https://orcid.org/0000-0003-4294-2541"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruqing Zhang","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, ICT, CAS; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, ICT, CAS; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088621320","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, ICT, CAS; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, ICT, CAS; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006971161","display_name":"Yixing Fan","orcid":"https://orcid.org/0000-0003-4317-2702"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Fan","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, ICT, CAS; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, ICT, CAS; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, ICT, CAS; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, ICT, CAS; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12020253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3858","last_page":"3862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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":0.9945999979972839,"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/discriminative-model","display_name":"Discriminative model","score":0.8974148035049438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8346874713897705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.65924471616745},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6490667462348938},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5985759496688843},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5588772296905518},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5471183657646179},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5328102111816406},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4479522109031677},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4461195468902588},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38319557905197144},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3589567542076111}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8974148035049438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8346874713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.65924471616745},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6490667462348938},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5985759496688843},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5588772296905518},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5471183657646179},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5328102111816406},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4479522109031677},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4461195468902588},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38319557905197144},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3589567542076111},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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:10.1145/3511808.3557582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557582","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557582","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":{"id":"doi:10.1145/3511808.3557582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557582","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557582","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1084062135","display_name":null,"funder_award_id":"20144310","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G1101359642","display_name":null,"funder_award_id":"No. 62006218 and 61902381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1420860423","display_name":null,"funder_award_id":"62006218 and 61902381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1731793062","display_name":null,"funder_award_id":"20144310 and 2021100","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G3317933164","display_name":null,"funder_award_id":"No. 62006218","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306316937.pdf","grobid_xml":"https://content.openalex.org/works/W4306316937.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2169213601","https://openalex.org/W2747909401","https://openalex.org/W2948947170","https://openalex.org/W2987861506","https://openalex.org/W3023238803","https://openalex.org/W3034912391","https://openalex.org/W3099700870","https://openalex.org/W3137609883","https://openalex.org/W3175111331","https://openalex.org/W4251326898"],"related_works":["https://openalex.org/W2888228969","https://openalex.org/W1602056621","https://openalex.org/W4287995534","https://openalex.org/W2747680751","https://openalex.org/W4377703168","https://openalex.org/W3154872984","https://openalex.org/W4280575577","https://openalex.org/W3023676446","https://openalex.org/W3177381119","https://openalex.org/W2969862959"],"abstract_inverted_index":{"Dense":[0],"retrieval":[1,10,165,173],"(DR)":[2],"has":[3,33],"shown":[4],"promising":[5],"results":[6],"in":[7,38,71,114],"many":[8],"information":[9],"(IR)":[11],"related":[12],"tasks,":[13],"whose":[14],"foundation":[15],"is":[16,90],"high-quality":[17],"text":[18,31,94,148,157],"representations":[19,43],"for":[20,85,154],"effective":[21,128],"search.":[22],"Taking":[23],"the":[24,30,41,50,56,67,115,135,142,151,155,171],"pre-trained":[25],"language":[26,80],"models":[27],"(PLMs)":[28],"as":[29,60],"encoders":[32],"become":[34],"a":[35,78,92,125,147],"popular":[36],"choice":[37],"DR.":[39,86],"However,":[40],"learned":[42],"based":[44],"on":[45,141,162],"these":[46],"PLMs":[47,61],"often":[48],"lose":[49],"discriminative":[51,79,103],"power,":[52],"and":[53],"thus":[54],"hurt":[55],"recall":[57],"performance,":[58],"particularly":[59],"consider":[62],"too":[63],"much":[64],"content":[65],"of":[66,146],"input":[68],"texts.":[69],"Therefore,":[70],"this":[72],"work,":[73],"we":[74,123],"propose":[75],"to":[76,99,133],"pre-train":[77],"representation":[81,95],"model,":[82],"called":[83,131],"DiscBERT,":[84],"The":[87],"key":[88],"idea":[89],"that":[91,105],"good":[93],"should":[96],"be":[97],"able":[98],"automatically":[100],"keep":[101],"those":[102],"features":[104],"could":[106],"well":[107],"distinguish":[108],"different":[109],"texts":[110],"from":[111],"each":[112],"other":[113],"semantic":[116],"space.":[117],"Specifically,":[118],"inspired":[119],"by":[120],"knowledge":[121,137,153],"distillation,":[122],"employ":[124],"simple":[126],"yet":[127],"training":[129,140],"method,":[130],"self-teaching,":[132],"distill":[134],"model's":[136,152],"constructed":[138],"when":[139],"sampled":[143],"representative":[144],"tokens":[145],"sequence":[149],"into":[150],"entire":[156],"sequence.":[158],"By":[159],"further":[160],"fine-tuning":[161],"publicly":[163],"available":[164],"benchmark":[166],"datasets,":[167],"DiscBERT":[168],"can":[169],"outperform":[170],"state-of-the-art":[172],"methods.":[174]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}