{"id":"https://openalex.org/W2988395732","doi":"https://doi.org/10.18653/v1/d19-6107","title":"Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining","display_name":"Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2988395732","doi":"https://doi.org/10.18653/v1/d19-6107","mag":"2988395732"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-6107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6107","pdf_url":"https://www.aclweb.org/anthology/D19-6107.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-6107.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022703491","display_name":"Xiaoman Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoman Pan","raw_affiliation_strings":["Bardolph is"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bardolph is","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065990625","display_name":"Thamme Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thamme Gowda","raw_affiliation_strings":["Information Sciences Institute, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075033889","display_name":"Heng Ji","orcid":"https://orcid.org/0000-0002-0464-7966"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Ji","raw_affiliation_strings":["Bardolph is","Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bardolph is","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000874697","display_name":"Jonathan May","orcid":"https://orcid.org/0000-0002-5284-477X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan May","raw_affiliation_strings":["Bardolph is","Information Sciences Institute, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bardolph is","institution_ids":[]},{"raw_affiliation_string":"Information Sciences Institute, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051632259","display_name":"S.L. Miller","orcid":"https://orcid.org/0009-0003-3345-6346"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Miller","raw_affiliation_strings":["Bardolph is","Information Sciences Institute, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bardolph is","institution_ids":[]},{"raw_affiliation_string":"Information Sciences Institute, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5784,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76610131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"66"},"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":0.9998999834060669,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9970999956130981,"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":0.8864551782608032},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7358177304267883},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.6890681982040405},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.623075008392334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6009380221366882},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5741004943847656},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.501467227935791},{"id":"https://openalex.org/keywords/linguistic-universal","display_name":"Linguistic universal","score":0.47877585887908936},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4651094079017639},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.43835994601249695},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4307236671447754},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3327261209487915},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16295430064201355},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13451212644577026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8864551782608032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7358177304267883},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.6890681982040405},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.623075008392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6009380221366882},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5741004943847656},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.501467227935791},{"id":"https://openalex.org/C79078291","wikidata":"https://www.wikidata.org/wiki/Q980142","display_name":"Linguistic universal","level":3,"score":0.47877585887908936},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4651094079017639},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.43835994601249695},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4307236671447754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3327261209487915},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16295430064201355},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13451212644577026},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.0},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d19-6107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6107","pdf_url":"https://www.aclweb.org/anthology/D19-6107.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-6107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6107","pdf_url":"https://www.aclweb.org/anthology/D19-6107.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G523448137","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8092615179","display_name":null,"funder_award_id":"HR0011-15-C-0115","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8810978190","display_name":null,"funder_award_id":"FA8650-17-C-9116","funder_id":"https://openalex.org/F4320312530","funder_display_name":"Office of the Director of National Intelligence"}],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320337349","display_name":"NIH Office of the Director","ror":"https://ror.org/00fj8a872"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2988395732.pdf","grobid_xml":"https://content.openalex.org/works/W2988395732.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W11298561","https://openalex.org/W13944552","https://openalex.org/W86887328","https://openalex.org/W102708294","https://openalex.org/W151066029","https://openalex.org/W342285082","https://openalex.org/W1614298861","https://openalex.org/W1678356000","https://openalex.org/W1713614699","https://openalex.org/W2009169514","https://openalex.org/W2022166150","https://openalex.org/W2100341149","https://openalex.org/W2118090838","https://openalex.org/W2126725946","https://openalex.org/W2151048449","https://openalex.org/W2153579005","https://openalex.org/W2158028897","https://openalex.org/W2250646737","https://openalex.org/W2250869925","https://openalex.org/W2251033195","https://openalex.org/W2251305270","https://openalex.org/W2251765408","https://openalex.org/W2270364989","https://openalex.org/W2294774419","https://openalex.org/W2461871142","https://openalex.org/W2512924740","https://openalex.org/W2552553554","https://openalex.org/W2594021297","https://openalex.org/W2739533097","https://openalex.org/W2739862013","https://openalex.org/W2740132093","https://openalex.org/W2741602058","https://openalex.org/W2771873754","https://openalex.org/W2798389157","https://openalex.org/W2805216012","https://openalex.org/W2891328459","https://openalex.org/W2949405462","https://openalex.org/W2950577311","https://openalex.org/W2952190837","https://openalex.org/W2962732637","https://openalex.org/W2962739703","https://openalex.org/W2962784628","https://openalex.org/W2963118869","https://openalex.org/W2963324947","https://openalex.org/W2963403868","https://openalex.org/W2963419157","https://openalex.org/W2963855739","https://openalex.org/W2963973577","https://openalex.org/W2964109726","https://openalex.org/W2964266061","https://openalex.org/W4294170691","https://openalex.org/W4297748452","https://openalex.org/W4299579390","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2375873920","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2849310602","https://openalex.org/W2597655663","https://openalex.org/W4286432911"],"abstract_inverted_index":{"Entities,":[0],"which":[1],"refer":[2],"to":[3,21,37,122,148,177],"distinct":[4],"objects":[5],"in":[6,58,67,75,118,126,187],"the":[7,59,68,76,113,119,127,145,165,169,194,199],"real":[8],"world,":[9],"can":[10,95,100],"be":[11],"viewed":[12],"as":[13,18],"language":[14,61,70,78,121,185],"universals":[15],"and":[16,27,47,84,168,172,198],"used":[17],"effective":[19],"signals":[20],"generate":[22,38],"less":[23],"ambiguous":[24],"semantic":[25],"representations":[26],"align":[28],"multiple":[29],"languages.":[30],"We":[31,53],"propose":[32],"a":[33,43],"novel":[34],"method,":[35],"CLEW,":[36],"cross-lingual":[39,81,135,155],"data":[40,92],"that":[41,123,141],"is":[42,193],"mix":[44],"of":[45,91,115,124],"entities":[46,98,125],"contextual":[48,116],"words":[49,117],"based":[50],"on":[51,163],"Wikipedia.":[52,188],"replace":[54],"each":[55],"anchor":[56],"link":[57],"source":[60,77,120],"with":[62],"its":[63],"corresponding":[64],"entity":[65,83,136,156],"title":[66],"target":[69,128],"if":[71],"it":[72,132,159,176],"exists,":[73],"or":[74],"otherwise.":[79],"A":[80],"joint":[82],"word":[85],"embedding":[86],"learned":[87],"from":[88],"this":[89,107],"kind":[90],"not":[93],"only":[94],"disambiguate":[96],"linkable":[97],"but":[99],"also":[101],"effectively":[102],"represent":[103],"unlinkable":[104],"entities.":[105],"Because":[106],"multilingual":[108],"common":[109],"space":[110],"directly":[111],"relates":[112],"semantics":[114],"language,":[129],"we":[130,174],"leverage":[131],"for":[133,153,181],"unsupervised":[134,154],"linking.":[137,157],"Experimental":[138],"results":[139],"show":[140],"CLEW":[142],"significantly":[143],"advances":[144],"state-of-the-art:":[146],"up":[147],"3.1%":[149],"absolute":[150],"Fscore":[151],"gain":[152],"Moreover,":[158],"provides":[160],"reliable":[161],"alignment":[162],"both":[164],"word/entity":[166],"level":[167],"sentence":[170],"level,":[171],"thus":[173],"use":[175],"mine":[178],"parallel":[179],"sentences":[180],"all":[182],"302":[183],"2":[184],"pairs":[186],"1":[189],"*":[190,191],"Friday":[192],"day":[195,200],"after":[196],"Thursday":[197],"before":[201],"Saturday":[202],".":[203]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}