{"id":"https://openalex.org/W4396722822","doi":"https://doi.org/10.1145/3589334.3645498","title":"Entity Disambiguation with Extreme Multi-label Ranking","display_name":"Entity Disambiguation with Extreme Multi-label Ranking","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396722822","doi":"https://doi.org/10.1145/3589334.3645498"},"language":"en","primary_location":{"id":"doi:10.1145/3589334.3645498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589334.3645498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-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/A5048749901","display_name":"Jyun\u2010Yu Jiang","orcid":"https://orcid.org/0000-0002-1753-8099"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jyun-Yu Jiang","raw_affiliation_strings":["Amazon Search, Palo Alto, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006559148","display_name":"Wei-Cheng Chang","orcid":"https://orcid.org/0000-0002-5646-9356"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Chang","raw_affiliation_strings":["Amazon Search, Palo Alto, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101969233","display_name":"Jiong Zhang","orcid":"https://orcid.org/0000-0003-3192-3281"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiong Zhang","raw_affiliation_strings":["Amazon Search, Palo Alto, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010841999","display_name":"Cho\u2010Jui Hsieh","orcid":"https://orcid.org/0000-0002-3520-9627"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cho-Jui Hsieh","raw_affiliation_strings":["University of California, Los Angeles & Google, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles & Google, Los Angeles, USA","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023183059","display_name":"Hsiang\u2010Fu Yu","orcid":"https://orcid.org/0000-0001-5235-2962"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsiang-Fu Yu","raw_affiliation_strings":["Amazon Search, Palo Alto, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048749901"],"corresponding_institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"],"apc_list":null,"apc_paid":null,"fwci":0.8084,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74850315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4172","last_page":"4180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9962999820709229,"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/T10028","display_name":"Topic Modeling","score":0.9945999979972839,"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":0.7627376317977905},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6130820512771606},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45817825198173523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42287978529930115},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4028449058532715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627376317977905},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6130820512771606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45817825198173523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42287978529930115},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4028449058532715}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589334.3645498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589334.3645498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.44999998807907104,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1554540371","https://openalex.org/W2031812225","https://openalex.org/W2040916592","https://openalex.org/W2127289991","https://openalex.org/W2295227292","https://openalex.org/W2594284271","https://openalex.org/W2612773933","https://openalex.org/W2788125153","https://openalex.org/W2912993660","https://openalex.org/W2963633290","https://openalex.org/W2963691861","https://openalex.org/W2964167098","https://openalex.org/W2970641574","https://openalex.org/W2970671085","https://openalex.org/W2979826702","https://openalex.org/W2981852735","https://openalex.org/W3027879771","https://openalex.org/W3034999214","https://openalex.org/W3104748221","https://openalex.org/W4285286514","https://openalex.org/W4287887524","https://openalex.org/W4288089799","https://openalex.org/W4290877723","https://openalex.org/W4292215729","https://openalex.org/W4385565376"],"related_works":["https://openalex.org/W2118564381","https://openalex.org/W2163901716","https://openalex.org/W2152204162","https://openalex.org/W2739821120","https://openalex.org/W2088097596","https://openalex.org/W2150136235","https://openalex.org/W2026095310","https://openalex.org/W2140661912","https://openalex.org/W2037724912","https://openalex.org/W2056806613"],"abstract_inverted_index":{"Entity":[0,56],"disambiguation":[1],"is":[2,71],"one":[3],"of":[4],"the":[5,41,83,114,141,173,178,194,207],"most":[6],"important":[7],"natural":[8],"language":[9],"tasks":[10],"to":[11,29,59,74,103,128,199],"identify":[12],"entities":[13,77],"behind":[14],"ambiguous":[15],"surface":[16],"mentions":[17],"within":[18],"a":[19,49,105,126,169,190],"knowledge":[20],"base.":[21],"Although":[22],"many":[23],"recent":[24],"studies":[25],"apply":[26],"deep":[27,123,170],"learning":[28,109],"achieve":[30,129],"decent":[31],"results,":[32],"they":[33],"need":[34],"exhausting":[35],"pre-training":[36],"and":[37,144,154,161,217],"mediocre":[38],"recall":[39,75,157],"in":[40,183,215,219],"retrieval":[42,84,212],"stage.":[43],"In":[44,202],"this":[45,61],"paper,":[46],"we":[47],"propose":[48],"novel":[50],"framework,":[51],"eXtreme":[52],"Multi-label":[53],"Ranking":[54],"for":[55,159,209],"Disambiguation":[57],"(XMRED),":[58],"address":[60],"challenge.":[62],"An":[63],"efficient":[64],"zero-shot":[65,146,162],"entity":[66,111],"retriever":[67],"with":[68,117,164,189],"auxiliary":[69],"data":[70],"first":[72,98],"pre-trained":[73],"relevant":[76],"based":[78,132,139],"on":[79,133,140,187,193],"linear":[80],"models.":[81],"Specifically,":[82],"process":[85],"can":[86],"be":[87],"considered":[88],"as":[89,125,172],"an":[90],"extreme":[91],"multi-label":[92],"ranking":[93],"(XMR)":[94],"task.":[95],"Entities":[96],"are":[97],"clustered":[99],"at":[100],"different":[101],"scales":[102],"form":[104],"label":[106,115],"tree,":[107],"thereby":[108],"multi-scale":[110],"retrievers":[112],"over":[113,155],"tree":[116],"high":[118,130],"recall.":[119],"Moreover,":[120],"XMRED":[121,151,175,204],"applies":[122],"cross-encoder":[124,171],"re-ranker":[127],"precision":[131],"high-quality":[134],"candidates.":[135],"Extensive":[136],"experimental":[137],"results":[138],"AIDA-CoNLL":[142],"benchmark":[143],"five":[145],"testing":[147],"datasets":[148,163],"demonstrate":[149],"that":[150],"obtains":[152],"98%":[153],"95%":[156],"scores":[158,186],"in-domain":[160],"top-10":[165],"retrieved":[166],"entities.":[167],"With":[168],"re-ranker,":[174],"further":[176],"outperforms":[177],"previous":[179],"state-of-the-art":[180,208],"by":[181,213],"1.74%":[182],"In-KB":[184],"micro-F1":[185],"average":[188],"significant":[191],"improvement":[192],"training":[195],"efficiency":[196],"from":[197],"days":[198],"3.48":[200],"hours.":[201],"addition,":[203],"also":[205],"beats":[206],"page-level":[210],"document":[211],"2.38%":[214],"accuracy":[216],"1.90%":[218],"recall@5.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}