{"id":"https://openalex.org/W4413683006","doi":"https://doi.org/10.1145/3764662","title":"A Model-agnostic Pre-training Framework for Search Result Diversification","display_name":"A Model-agnostic Pre-training Framework for Search Result Diversification","publication_year":2025,"publication_date":"2025-08-26","ids":{"openalex":"https://openalex.org/W4413683006","doi":"https://doi.org/10.1145/3764662"},"language":"en","primary_location":{"id":"doi:10.1145/3764662","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3764662","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3764662","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3764662","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079867869","display_name":"Zhirui Deng","orcid":"https://orcid.org/0000-0001-8952-7666"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhirui Deng","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","Gaoling School of Artificial Intelligence, Renmin University of China, China"],"raw_orcid":"https://orcid.org/0000-0001-8952-7666","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010558184","display_name":"Zhicheng Dou","orcid":"https://orcid.org/0000-0002-9781-948X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Dou","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","Gaoling School of Artificial Intelligence, Renmin University of China, China"],"raw_orcid":"https://orcid.org/0000-0002-9781-948X","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007186741","display_name":"Yutao Zhu","orcid":"https://orcid.org/0000-0002-9432-3251"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Zhu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","Gaoling School of Artificial Intelligence, Renmin University of China, China"],"raw_orcid":"https://orcid.org/0000-0002-9432-3251","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","Gaoling School of Artificial Intelligence, Renmin University of China, China"],"raw_orcid":"https://orcid.org/0000-0002-9777-9676","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11115437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"1","first_page":"1","last_page":"23"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9979000091552734,"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/diversification","display_name":"Diversification (marketing strategy)","score":0.7852290868759155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5704420804977417},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5638287663459778},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.2919606864452362},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13505172729492188},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.1256924569606781}],"concepts":[{"id":"https://openalex.org/C180916674","wikidata":"https://www.wikidata.org/wiki/Q3711935","display_name":"Diversification (marketing strategy)","level":2,"score":0.7852290868759155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5704420804977417},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5638287663459778},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.2919606864452362},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13505172729492188},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.1256924569606781},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3764662","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3764662","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3764662","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3764662","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3764662","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3764662","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G228125052","display_name":null,"funder_award_id":"62272467","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/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413683006.pdf","grobid_xml":"https://content.openalex.org/works/W4413683006.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1498594556","https://openalex.org/W1566289585","https://openalex.org/W1990473707","https://openalex.org/W2023188792","https://openalex.org/W2047804176","https://openalex.org/W2047952076","https://openalex.org/W2091158010","https://openalex.org/W2113640060","https://openalex.org/W2132314908","https://openalex.org/W2148367931","https://openalex.org/W2151875087","https://openalex.org/W2154724067","https://openalex.org/W2157391629","https://openalex.org/W2168717408","https://openalex.org/W2337233909","https://openalex.org/W2560674852","https://openalex.org/W2739826497","https://openalex.org/W2945127593","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W3003611599","https://openalex.org/W3034950638","https://openalex.org/W3046020243","https://openalex.org/W3083591248","https://openalex.org/W3093493377","https://openalex.org/W3093570284","https://openalex.org/W3094347401","https://openalex.org/W3099446234","https://openalex.org/W3115195983","https://openalex.org/W3132466668","https://openalex.org/W3138773240","https://openalex.org/W3152562554","https://openalex.org/W3155865710","https://openalex.org/W3156636935","https://openalex.org/W3196020299","https://openalex.org/W3208801308","https://openalex.org/W4288072953","https://openalex.org/W4290877092","https://openalex.org/W4320813768","https://openalex.org/W4387847693","https://openalex.org/W4388106512","https://openalex.org/W4392384899","https://openalex.org/W4392849580","https://openalex.org/W4400528511","https://openalex.org/W4412377028"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W4389391504","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4301410663"],"abstract_inverted_index":{"Search":[0],"result":[1,21,181],"diversification":[2,22],"focuses":[3],"on":[4],"providing":[5],"relevant":[6],"and":[7,18,43,45,71,121,175],"diverse":[8],"documents":[9],"covering":[10],"different":[11],"users\u2019":[12,38],"intents.":[13],"Intuitively,":[14],"training":[15,29,53],"an":[16],"effective":[17],"stable":[19],"search":[20,39,180],"model":[23,149,161],"needs":[24],"a":[25,79,111],"large":[26],"amount":[27],"of":[28,68,167,177],"data.":[30],"Unfortunately,":[31],"annotating":[32],"such":[33],"data":[34,86],"that":[35,63,158],"encompass":[36],"real":[37],"intents":[40],"is":[41,142],"expensive":[42],"time-consuming,":[44],"most":[46],"existing":[47,169],"models":[48],"are":[49,134],"trained":[50],"with":[51],"limited":[52],"data,":[54,73],"which":[55,141,171],"might":[56],"lead":[57],"to":[58,87,96,116,126,136],"unsatisfactory":[59],"ranking":[60],"results.":[61],"Given":[62],"Wikipedia":[64,85],"contains":[65],"massive":[66],"amounts":[67],"rigorous":[69],"editorial":[70],"well-structured":[72],"in":[74,150],"this":[75],"article,":[76],"we":[77,92],"propose":[78,110],"pre-training":[80,178],"framework":[81],"leveraging":[82],"the":[83,102,123,138,146,151,165,173],"large-scale":[84],"build":[88],"weak-supervised":[89],"signals.":[90],"Specifically,":[91],"introduce":[93],"four":[94],"strategies":[95],"extract":[97],"paired":[98],"supervised":[99],"signals":[100],"reflecting":[101],"subtopic":[103,129],"coverage":[104],"information":[105],"from":[106],"Wikipedia.":[107],"We":[108],"also":[109],"subtopic-disentangled":[112],"negative":[113,119],"sampling":[114],"strategy":[115],"sample":[117],"hard":[118],"samples":[120],"enhance":[122],"model\u2019s":[124],"ability":[125],"identify":[127],"subtle":[128],"differences.":[130],"Four":[131],"auxiliary":[132],"tasks":[133],"devised":[135],"pre-train":[137],"Transformer":[139],"model,":[140],"further":[143],"adopted":[144],"as":[145],"representation":[147],"generation":[148],"downstream":[152],"diversified":[153],"ranking.":[154],"Experimental":[155],"results":[156],"demonstrate":[157],"our":[159],"pre-trained":[160],"can":[162],"significantly":[163],"improve":[164],"performance":[166],"several":[168],"models,":[170],"confirms":[172],"effectiveness":[174],"scalability":[176],"for":[179],"diversification.":[182]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}