{"id":"https://openalex.org/W4224865658","doi":"https://doi.org/10.1145/3477495.3531772","title":"Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction","display_name":"Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction","publication_year":2022,"publication_date":"2022-07-06","ids":{"openalex":"https://openalex.org/W4224865658","doi":"https://doi.org/10.1145/3477495.3531772"},"language":"en","primary_location":{"id":"doi:10.1145/3477495.3531772","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3477495.3531772","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3477495.3531772","source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","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 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3477495.3531772","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056848863","display_name":"Xinyu Ma","orcid":"https://orcid.org/0000-0002-5511-9370"},"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":true,"raw_author_name":"Xinyu Ma","raw_affiliation_strings":["ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"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":["ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"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":["ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"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":["ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"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":["ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ICT, CAS & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056848863"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":3.3384,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93645999,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"848","last_page":"858"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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":0.9975000023841858,"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/autoencoder","display_name":"Autoencoder","score":0.8365733623504639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8240125179290771},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8135558366775513},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7001957893371582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5869573354721069},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5438045859336853},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5393962264060974},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5269445180892944},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5122910737991333},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4569883346557617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39249667525291443},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3858005702495575},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3760727047920227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3568902313709259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3515104055404663},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.057487040758132935}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8365733623504639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8240125179290771},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8135558366775513},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7001957893371582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5869573354721069},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5438045859336853},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5393962264060974},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5269445180892944},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5122910737991333},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4569883346557617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39249667525291443},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3858005702495575},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3760727047920227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3568902313709259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3515104055404663},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.057487040758132935},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3477495.3531772","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3477495.3531772","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3477495.3531772","source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","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 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2204.10641","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.10641","pdf_url":"https://arxiv.org/pdf/2204.10641","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:10.1145/3477495.3531772","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3477495.3531772","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3477495.3531772","source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","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 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"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/G1185699554","display_name":null,"funder_award_id":"61872338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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"},{"id":"https://openalex.org/G4171408361","display_name":null,"funder_award_id":"62006218, 61902381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4758593323","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/G7539905487","display_name":null,"funder_award_id":"202110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7617174747","display_name":null,"funder_award_id":"No. 62006218 61902381 and 61872338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8143428411","display_name":null,"funder_award_id":"cstc2017jcyjBX0059","funder_id":"https://openalex.org/F4320321550","funder_display_name":"Chongqing Science and Technology Commission"},{"id":"https://openalex.org/G8752928798","display_name":null,"funder_award_id":"62006218, 61902381, and 61872338","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/F4320321550","display_name":"Chongqing Science and Technology Commission","ror":"https://ror.org/05w9erc61"},{"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4224865658.pdf","grobid_xml":"https://content.openalex.org/works/W4224865658.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W2270070752","https://openalex.org/W2296073425","https://openalex.org/W2560674852","https://openalex.org/W2938830017","https://openalex.org/W2951434086","https://openalex.org/W2951534261","https://openalex.org/W2963341956","https://openalex.org/W2964184826","https://openalex.org/W2965373594","https://openalex.org/W2982096936","https://openalex.org/W2995289474","https://openalex.org/W3005296017","https://openalex.org/W3005680577","https://openalex.org/W3021397474","https://openalex.org/W3023238803","https://openalex.org/W3034439313","https://openalex.org/W3035060554","https://openalex.org/W3037128914","https://openalex.org/W3093570284","https://openalex.org/W3098708719","https://openalex.org/W3099700870","https://openalex.org/W3115195983","https://openalex.org/W3118668786","https://openalex.org/W3137305332","https://openalex.org/W3152562554","https://openalex.org/W3153055969","https://openalex.org/W3154670582","https://openalex.org/W3154898636","https://openalex.org/W3155895380","https://openalex.org/W3156636935","https://openalex.org/W3160883893","https://openalex.org/W3166441238","https://openalex.org/W3168875417","https://openalex.org/W3173783447","https://openalex.org/W3175111331","https://openalex.org/W3175627818","https://openalex.org/W3184918446","https://openalex.org/W3198098536","https://openalex.org/W3198963570","https://openalex.org/W3212725701","https://openalex.org/W4206121183","https://openalex.org/W4206633947","https://openalex.org/W4214740783","https://openalex.org/W4221164176","https://openalex.org/W4238846128","https://openalex.org/W4252076394","https://openalex.org/W4287592659","https://openalex.org/W4287812705","https://openalex.org/W4293111695","https://openalex.org/W4327640211"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"Dense":[0],"retrieval":[1,9,38,131,145],"has":[2,65],"shown":[3,27],"promising":[4],"results":[5],"in":[6,73],"many":[7],"information":[8],"(IR)":[10],"related":[11],"tasks,":[12],"whose":[13],"foundation":[14],"is":[15,50],"high-quality":[16],"text":[17,106],"representation":[18],"learning":[19,113],"for":[20,143],"effective":[21],"search.":[22],"Some":[23],"recent":[24],"studies":[25],"have":[26],"that":[28,47,135],"autoencoder-based":[29],"language":[30],"models":[31],"are":[32],"able":[33],"to":[34,53,84],"boost":[35],"the":[36,56,66,70,86,92,96,110,119,123],"dense":[37,144],"performance":[39],"using":[40],"a":[41,62,78],"weak":[42,63],"decoder.":[43],"However,":[44],"we":[45,76,101],"argue":[46],"1)":[48,103],"it":[49],"not":[51],"discriminative":[52,105],"decode":[54],"all":[55],"input":[57],"texts":[58],"and,":[59,116],"2)":[60,117],"even":[61],"decoder":[64,124],"bypass":[67,120],"effect":[68,121],"on":[69],"encoder.":[71],"Therefore,":[72],"this":[74,99],"work,":[75],"introduce":[77],"novel":[79],"contrastive":[80,112],"span":[81],"prediction":[82],"task":[83],"pre-train":[85],"encoder":[87],"alone,":[88],"but":[89],"still":[90],"retain":[91],"bottleneck":[93],"ability":[94],"of":[95,122],"autoencoder.":[97],"In":[98],"way,":[100],"can":[102,138],"learn":[104],"representations":[107],"efficiently":[108],"with":[109],"group-wise":[111],"over":[114,128],"spans":[115],"avoid":[118],"thoroughly.":[125],"Comprehensive":[126],"experiments":[127],"publicly":[129],"available":[130],"benchmark":[132],"datasets":[133],"show":[134],"our":[136],"approach":[137],"outperform":[139],"existing":[140],"pre-training":[141],"methods":[142],"significantly.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2022-04-27T00:00:00"}