{"id":"https://openalex.org/W3014809049","doi":"https://doi.org/10.1162/tacl_a_00303","title":"Improving Candidate Generation for Low-resource Cross-lingual Entity Linking","display_name":"Improving Candidate Generation for Low-resource Cross-lingual Entity Linking","publication_year":2020,"publication_date":"2020-03-31","ids":{"openalex":"https://openalex.org/W3014809049","doi":"https://doi.org/10.1162/tacl_a_00303","mag":"3014809049"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00303","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00303","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00303/1923805/tacl_a_00303.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00303/1923805/tacl_a_00303.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071869999","display_name":"Shuyan Zhou","orcid":"https://orcid.org/0000-0001-8815-5098"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuyan Zhou","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Language Technologies Institute, Carnegie Mellon University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014428509","display_name":"Shruti Rijhwani","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shruti Rijhwani","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Language Technologies Institute, Carnegie Mellon University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002499277","display_name":"John Wieting","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Wieting","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Language Technologies Institute, Carnegie Mellon University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110349922","display_name":"Jaime Carbonell","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaime Carbonell","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Language Technologies Institute, Carnegie Mellon University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Language Technologies Institute, Carnegie Mellon University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002499277","https://openalex.org/A5014428509","https://openalex.org/A5068811427","https://openalex.org/A5071869999","https://openalex.org/A5110349922"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.7681,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.87937092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"8","issue":null,"first_page":"109","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9965000152587891,"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":0.8556484580039978},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5844136476516724},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5266680121421814},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5066457390785217},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48798125982284546},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4812186062335968},{"id":"https://openalex.org/keywords/realm","display_name":"Realm","score":0.4653260409832001},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.44380828738212585},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4238338768482208},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4220649302005768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4033609628677368},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.36269646883010864},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12775903940200806}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8556484580039978},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5844136476516724},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5266680121421814},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5066457390785217},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48798125982284546},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4812186062335968},{"id":"https://openalex.org/C2778757428","wikidata":"https://www.wikidata.org/wiki/Q1250464","display_name":"Realm","level":2,"score":0.4653260409832001},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44380828738212585},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4238338768482208},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4220649302005768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4033609628677368},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.36269646883010864},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12775903940200806},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00303","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00303","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00303/1923805/tacl_a_00303.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2c64a6c204be4c2988941b57c8961921","is_oa":true,"landing_page_url":"https://doaj.org/article/2c64a6c204be4c2988941b57c8961921","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 8, Pp 109-124 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00303","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00303","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00303/1923805/tacl_a_00303.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W11298561","https://openalex.org/W86887328","https://openalex.org/W136741500","https://openalex.org/W1490960179","https://openalex.org/W1502957213","https://openalex.org/W1516184288","https://openalex.org/W1541691357","https://openalex.org/W1548663377","https://openalex.org/W1736726159","https://openalex.org/W1818534184","https://openalex.org/W1847618513","https://openalex.org/W1964189668","https://openalex.org/W2019614587","https://openalex.org/W2140406733","https://openalex.org/W2170240176","https://openalex.org/W2170973209","https://openalex.org/W2250554077","https://openalex.org/W2250750514","https://openalex.org/W2461871142","https://openalex.org/W2463895987","https://openalex.org/W2471692228","https://openalex.org/W2479758238","https://openalex.org/W2516125976","https://openalex.org/W2521118911","https://openalex.org/W2524182563","https://openalex.org/W2541443726","https://openalex.org/W2559655401","https://openalex.org/W2573062194","https://openalex.org/W2597601064","https://openalex.org/W2598684926","https://openalex.org/W2599674900","https://openalex.org/W2612690371","https://openalex.org/W2612773933","https://openalex.org/W2613223139","https://openalex.org/W2621067739","https://openalex.org/W2742113707","https://openalex.org/W2753398138","https://openalex.org/W2762484717","https://openalex.org/W2788147795","https://openalex.org/W2799915114","https://openalex.org/W2804784869","https://openalex.org/W2805216012","https://openalex.org/W2805993470","https://openalex.org/W2888536529","https://openalex.org/W2890511566","https://openalex.org/W2891333118","https://openalex.org/W2899641520","https://openalex.org/W2913739034","https://openalex.org/W2947992883","https://openalex.org/W2963403868","https://openalex.org/W2963499246","https://openalex.org/W2963722184","https://openalex.org/W2963973577","https://openalex.org/W2964114970","https://openalex.org/W2964266061","https://openalex.org/W2968573267","https://openalex.org/W2970242339","https://openalex.org/W2977200951","https://openalex.org/W2998702515","https://openalex.org/W3087927280","https://openalex.org/W3088935248","https://openalex.org/W4235463181","https://openalex.org/W4238634189","https://openalex.org/W4241850027"],"related_works":["https://openalex.org/W2358294942","https://openalex.org/W1541691357","https://openalex.org/W2090135255","https://openalex.org/W2168409722","https://openalex.org/W2782437235","https://openalex.org/W2548972888","https://openalex.org/W2026505290","https://openalex.org/W1993715838","https://openalex.org/W2359088421","https://openalex.org/W2328532631"],"abstract_inverted_index":{"Cross-lingual":[0],"entity":[1,121,138],"linking":[2],"(XEL)":[3],"is":[4,27],"the":[5,39,55,85,90,101,116,135,146,149],"task":[6],"of":[7,25,34,57,148,177,196,201],"finding":[8],"referents":[9],"in":[10,54,89,96,179,198],"a":[11,32],"target-language":[12,40],"knowledge":[13],"base":[14],"(KB)":[15],"for":[16,42,87,125],"mentions":[17,139],"extracted":[18],"from":[19,38,49],"source-language":[20],"texts.":[21],"The":[22,154],"first":[23,114],"step":[24],"(X)EL":[26],"candidate":[28,36,122,182],"generation,":[29],"which":[30],"retrieves":[31],"list":[33],"plausible":[35],"entities":[37],"KB":[41,141],"each":[43],"mention.":[44],"Approaches":[45],"based":[46],"on":[47,165],"resources":[48,88,95],"Wikipedia":[50,74],"have":[51,80],"proven":[52],"successful":[53],"realm":[56],"relatively":[58],"high-resource":[59,108],"languages,":[60,99],"but":[61,100,158],"these":[62],"do":[63],"not":[64],"extend":[65],"well":[66],"to":[67,83,151],"low-resource":[68,91,126,152],"languages":[69,92],"with":[70,162,185],"few,":[71],"if":[72],"any,":[73],"pages.":[75],"Recently,":[76],"transfer":[77],"learning":[78],"methods":[79,124,155],"been":[81],"shown":[82],"reduce":[84,134],"demand":[86],"by":[93,119],"utilizing":[94],"closely":[97],"related":[98],"performance":[102],"still":[103],"lags":[104],"far":[105],"behind":[106],"their":[107],"counterparts.":[109],"In":[110],"this":[111],"paper,":[112],"we":[113],"assess":[115],"problems":[117],"faced":[118],"current":[120],"generation":[123],"XEL,":[127],"then":[128],"propose":[129],"three":[130],"improvements":[131],"that":[132,171],"(1)":[133],"disconnect":[136],"between":[137],"and":[140,143,169],"entries,":[142],"(2)":[144],"improve":[145],"robustness":[147],"model":[150,190],"scenarios.":[153],"are":[156],"simple,":[157],"effective:":[159],"We":[160],"experiment":[161],"our":[163],"approach":[164],"seven":[166],"XEL":[167],"datasets":[168],"find":[170],"they":[172],"yield":[173],"an":[174,193],"average":[175,194],"gain":[176,195],"16.9%":[178],"Top-30":[180],"gold":[181],"recall,":[183],"compared":[184],"state-of-the-art":[186],"baselines.":[187],"Our":[188],"improved":[189],"also":[191],"yields":[192],"7.9%":[197],"in-KB":[199],"accuracy":[200],"end-to-end":[202],"XEL.":[203],"1":[204]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}