{"id":"https://openalex.org/W3093570284","doi":"https://doi.org/10.1145/3437963.3441777","title":"PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval","display_name":"PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval","publication_year":2021,"publication_date":"2021-03-06","ids":{"openalex":"https://openalex.org/W3093570284","doi":"https://doi.org/10.1145/3437963.3441777","mag":"3093570284"},"language":"en","primary_location":{"id":"doi:10.1145/3437963.3441777","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437963.3441777","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437963.3441777","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3437963.3441777","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xinyu Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiafeng Guo","orcid":null},"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"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruqing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yixing Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiang Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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":"Xiang Ji","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xueqi Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":5.1785,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96093351,"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":"283","last_page":"291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9959999918937683,"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":0.9957000017166138,"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/language-model","display_name":"Language model","score":0.6008999943733215},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5490000247955322},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5364999771118164},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5260999798774719},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4659999907016754},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.398499995470047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800000011920929},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5907999873161316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5835999846458435},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5364999771118164},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4659999907016754},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36489999294281006},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.289000004529953},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3437963.3441777","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437963.3441777","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437963.3441777","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.10137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.10137","pdf_url":"https://arxiv.org/pdf/2010.10137","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:10.1145/3437963.3441777","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437963.3441777","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437963.3441777","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G438163229","display_name":null,"funder_award_id":"61722211, 61773362, 61872338, 62006218, 61902381","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3093570284.pdf","grobid_xml":"https://content.openalex.org/works/W3093570284.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1982314207","https://openalex.org/W2022871093","https://openalex.org/W2144578941","https://openalex.org/W2159665776","https://openalex.org/W2159981039","https://openalex.org/W2534136119","https://openalex.org/W2536015822","https://openalex.org/W2610935556","https://openalex.org/W2648699835","https://openalex.org/W2766284073","https://openalex.org/W2940927814","https://openalex.org/W2945127593","https://openalex.org/W2951434086","https://openalex.org/W2955732934","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2964012472","https://openalex.org/W4206765718","https://openalex.org/W4251326898","https://openalex.org/W6601141708"],"related_works":[],"abstract_inverted_index":{"Recently":[0],"pre-trained":[1],"language":[2,54,109],"representation":[3],"models":[4],"such":[5],"as":[6,70,119],"BERT":[7],"have":[8,28],"shown":[9],"great":[10],"success":[11],"when":[12],"fine-tuned":[13],"on":[14,81,152],"downstream":[15,157],"tasks":[16],"including":[17],"information":[18],"retrieval":[19,27,159],"(IR).":[20],"However,":[21],"pre-training":[22,168,172],"objectives":[23],"tailored":[24],"for":[25,44,56,92],"ad-hoc":[26,45,158],"not":[29],"been":[30],"well":[31],"explored.":[32],"In":[33],"this":[34,82],"paper,":[35],"we":[36,84,98],"propose":[37],"Pre-training":[38],"with":[39,114,142,170],"Representative":[40],"wOrds":[41],"Prediction":[42],"(PROP)":[43],"retrieval.":[46],"PROP":[47,161,178],"is":[48,68,117],"inspired":[49],"by":[50],"the":[51,59,66,71,77,86,107,112,123,128,133,137,143,185],"classical":[52],"statistical":[53],"model":[55,130],"IR,":[57],"specifically":[58],"query":[60,67],"likelihood":[61,116],"model,":[62,110],"which":[63],"assumes":[64],"that":[65,177],"generated":[69],"piece":[72],"of":[73,76,102,122,155],"text":[74],"representative":[75,87,121,156],"\"ideal\"":[78],"document.":[79,124],"Based":[80],"idea,":[83],"construct":[85],"words":[88],"prediction":[89],"(ROP)":[90],"task":[91],"pre-training.":[93],"Given":[94],"an":[95],"input":[96],"document,":[97],"sample":[99],"a":[100,153],"pair":[101],"word":[103,139],"sets":[104],"according":[105],"to":[106,131],"document":[108],"where":[111],"set":[113],"higher":[115],"deemed":[118],"more":[120],"We":[125,174],"then":[126],"pre-train":[127],"Transformer":[129],"predict":[132],"pairwise":[134],"preference":[135],"between":[136],"two":[138],"sets,":[140],"jointly":[141],"Masked":[144],"Language":[145],"Model":[146],"(MLM)":[147],"objective.":[148],"By":[149],"further":[150],"fine-tuning":[151],"variety":[154],"tasks,":[160],"achieves":[162],"significant":[163],"improvements":[164],"over":[165],"baselines":[166],"without":[167],"or":[169],"other":[171],"methods.":[173],"also":[175],"show":[176],"can":[179],"achieve":[180],"exciting":[181],"performance":[182],"under":[183],"both":[184],"zero-":[186],"and":[187],"low-resource":[188],"IR":[189],"settings.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":6}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2020-10-29T00:00:00"}