{"id":"https://openalex.org/W4388709718","doi":"https://doi.org/10.1109/tkde.2023.3332858","title":"WebUltron: An Ultimate Retriever on Webpages Under the Model-Centric Paradigm","display_name":"WebUltron: An Ultimate Retriever on Webpages Under the Model-Centric Paradigm","publication_year":2023,"publication_date":"2023-11-15","ids":{"openalex":"https://openalex.org/W4388709718","doi":"https://doi.org/10.1109/tkde.2023.3332858"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2023.3332858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3332858","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032133163","display_name":"Yujia Zhou","orcid":"https://orcid.org/0000-0002-3530-3787"},"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":"Yujia Zhou","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Beijing Key Laboratory of Big Data Management and Analysis Methods, DEKE, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3530-3787","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Beijing Key Laboratory of Big Data Management and Analysis Methods, DEKE, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084847804","display_name":"Jing Yao","orcid":"https://orcid.org/0000-0002-0527-6095"},"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":"Jing Yao","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Beijing Key Laboratory of Big Data Management and Analysis Methods, DEKE, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0527-6095","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Beijing Key Laboratory of Big Data Management and Analysis Methods, DEKE, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082046914","display_name":"Ledell Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ledell Wu","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"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, Beijing Key Laboratory of Big Data Management and Analysis Methods, DEKE, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9781-948X","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Beijing Key Laboratory of Big Data Management and Analysis Methods, DEKE, Renmin University of China, Beijing, 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, Beijing Key Laboratory of Big Data Management and Analysis Methods, DEKE, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9777-9676","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Beijing Key Laboratory of Big Data Management and Analysis Methods, DEKE, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6547,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75485921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"36","issue":"9","first_page":"4996","last_page":"5006"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9975000023841858,"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":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.8542086482048035},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7100376486778259},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6843997836112976},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6610608100891113},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5994399785995483},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5048370957374573},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4340653419494629},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4161585867404938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32571572065353394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8542086482048035},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7100376486778259},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6843997836112976},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6610608100891113},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5994399785995483},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5048370957374573},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4340653419494629},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4161585867404938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32571572065353394},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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:10.1109/tkde.2023.3332858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3332858","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3634295602","display_name":null,"funder_award_id":"61832017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5185422413","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u4e2a\u6027\u5316\u641c\u7d22\u6280\u672f\u7814\u7a76","funder_award_id":"61872370","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1973289172","https://openalex.org/W1979963107","https://openalex.org/W1981038351","https://openalex.org/W2077815765","https://openalex.org/W2124509324","https://openalex.org/W2250539671","https://openalex.org/W2536015822","https://openalex.org/W2610935556","https://openalex.org/W2896457183","https://openalex.org/W2912924812","https://openalex.org/W2937036051","https://openalex.org/W2962770891","https://openalex.org/W2965373594","https://openalex.org/W2998702515","https://openalex.org/W3007672467","https://openalex.org/W3021397474","https://openalex.org/W3037128914","https://openalex.org/W3099700870","https://openalex.org/W3100107515","https://openalex.org/W3145630588","https://openalex.org/W3155895380","https://openalex.org/W3157758108","https://openalex.org/W3185146124","https://openalex.org/W3194782062","https://openalex.org/W3209791570","https://openalex.org/W4221146749","https://openalex.org/W4221166196","https://openalex.org/W4223512675","https://openalex.org/W4236275144","https://openalex.org/W4252076394","https://openalex.org/W4252222626","https://openalex.org/W4283315779","https://openalex.org/W4287647122","https://openalex.org/W4288089799","https://openalex.org/W4320465836","https://openalex.org/W4385245566","https://openalex.org/W4385573970","https://openalex.org/W6636510571","https://openalex.org/W6729938257","https://openalex.org/W6757817989","https://openalex.org/W6761452495","https://openalex.org/W6762832483","https://openalex.org/W6766673545","https://openalex.org/W6769627184","https://openalex.org/W6774222543","https://openalex.org/W6778883912","https://openalex.org/W6779872132","https://openalex.org/W6780489933","https://openalex.org/W6783675033","https://openalex.org/W6810136073","https://openalex.org/W6810139940","https://openalex.org/W6810674654","https://openalex.org/W6839125180","https://openalex.org/W6850138286"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W3024364549","https://openalex.org/W4252684102","https://openalex.org/W2608983118","https://openalex.org/W2352307597","https://openalex.org/W1979633005","https://openalex.org/W4388431390","https://openalex.org/W4318719391","https://openalex.org/W2155531513","https://openalex.org/W2547703856"],"abstract_inverted_index":{"Document":[0],"retrieval":[1,25],"has":[2,11],"been":[3],"extensively":[4],"studied":[5],"within":[6,54],"theindex-retrieveframework":[7],"for":[8,43,58,150],"decades,":[9],"which":[10],"withstood":[12],"the":[13,22,49,55,69,76,89,143],"test":[14],"of":[15,51,71,91,145],"time.":[16],"However,":[17],"this":[18,34,66],"approach":[19],"inherently":[20],"segregates":[21],"indexing":[23],"and":[24,75,88,133],"processes,":[26],"preventing":[27],"a":[28,39,125],"cohesive,":[29],"end-to-end":[30,60],"optimization.":[31],"To":[32],"bridge":[33],"divide,":[35],"we":[36],"introduce":[37],"WebUltron,":[38],"revolutionary":[40],"model-centric":[41],"indexer":[42,67],"document":[44,52,72,151],"retrieval.":[45,61,152],"This":[46],"system":[47],"embeds":[48],"entirety":[50],"knowledge":[53],"model,":[56],"striving":[57],"seamless":[59],"Two":[62],"primary":[63],"challenges":[64],"with":[65,82,111],"are":[68],"representation":[70],"identifiers":[73],"(docids)":[74],"model's":[77],"training.":[78],"Current":[79],"methods":[80],"grapple":[81],"docids":[83],"that":[84,114],"lack":[85],"semantic":[86],"depth":[87],"constraints":[90],"limited":[92],"supervised":[93],"data,":[94],"making":[95],"scaling":[96],"up":[97],"to":[98],"larger":[99],"datasets":[100,141],"challenging.":[101],"Addressing":[102],"this,":[103],"we've":[104,123],"engineered":[105],"two":[106,139],"novel":[107],"docid":[108],"types":[109],"imbued":[110],"richer":[112],"semantics":[113],"also":[115],"streamline":[116],"model":[117],"inference.":[118],"Further":[119],"enhancing":[120],"WebUltron's":[121],"capabilities,":[122],"developed":[124],"three-stage":[126],"training":[127],"regimen,":[128],"leveraging":[129],"deeper":[130],"corpus":[131],"insights":[132],"fortifying":[134],"query-docid":[135],"relationships.":[136],"Experiments":[137],"on":[138],"public":[140],"demonstrate":[142],"superiority":[144],"WebUltron":[146],"over":[147],"advanced":[148],"baselines":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}