{"id":"https://openalex.org/W2742113707","doi":"https://doi.org/10.18653/v1/p17-1178","title":"Cross-lingual Name Tagging and Linking for 282 Languages","display_name":"Cross-lingual Name Tagging and Linking for 282 Languages","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2742113707","doi":"https://doi.org/10.18653/v1/p17-1178","mag":"2742113707"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-1178","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1178","pdf_url":"https://www.aclweb.org/anthology/P17-1178.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-1178.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022703491","display_name":"Xiaoman Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaoman Pan","raw_affiliation_strings":["Computer Science Department, Rensselaer Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103097182","display_name":"Boliang Zhang","orcid":"https://orcid.org/0009-0003-8767-340X"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boliang Zhang","raw_affiliation_strings":["Computer Science Department, Rensselaer Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"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":["Information Sciences Institute, University of Southern California"],"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/A5079518059","display_name":"Joel Nothman","orcid":"https://orcid.org/0000-0003-1497-3842"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Joel Nothman","raw_affiliation_strings":["Sydney Informatics Hub, University of Sydney"],"affiliations":[{"raw_affiliation_string":"Sydney Informatics Hub, University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106821597","display_name":"Kevin Knight","orcid":"https://orcid.org/0000-0001-9117-1718"},"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":"Kevin Knight","raw_affiliation_strings":["Information Sciences Institute, University of Southern California"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075033889","display_name":"Heng Ji","orcid":"https://orcid.org/0000-0002-0464-7966"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Ji","raw_affiliation_strings":["Computer Science Department, Rensselaer Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022703491"],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":12.2638,"has_fulltext":true,"cited_by_count":309,"citation_normalized_percentile":{"value":0.98802011,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1946","last_page":"1958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8580524921417236},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6596550345420837},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5358629822731018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.525439441204071},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.48663052916526794},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.46776363253593445},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.454574316740036},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.4517109990119934},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3805793225765228},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.2938348948955536},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20440036058425903}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8580524921417236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6596550345420837},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5358629822731018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.525439441204071},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48663052916526794},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.46776363253593445},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.454574316740036},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4517109990119934},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3805793225765228},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2938348948955536},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20440036058425903},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p17-1178","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1178","pdf_url":"https://www.aclweb.org/anthology/P17-1178.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-1178","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1178","pdf_url":"https://www.aclweb.org/anthology/P17-1178.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1171700966","display_name":null,"funder_award_id":"NSF CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2273398380","display_name":null,"funder_award_id":"NSF CAREER","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G3427823788","display_name":"CAREER:  Cross-Document Cross-Lingual Event Extraction and Tracking","funder_award_id":"1523198","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3429874898","display_name":null,"funder_award_id":"LORELEI","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G3693556586","display_name":null,"funder_award_id":"2-004","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3911920403","display_name":null,"funder_award_id":"FA8750-13-2-0041","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5524522455","display_name":null,"funder_award_id":"DARPA","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G6526725481","display_name":null,"funder_award_id":"W911NF-10-1-053","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7584587656","display_name":null,"funder_award_id":"15231","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2742113707.pdf","grobid_xml":"https://content.openalex.org/works/W2742113707.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W130452239","https://openalex.org/W630883066","https://openalex.org/W638568100","https://openalex.org/W785060174","https://openalex.org/W804133461","https://openalex.org/W1502473750","https://openalex.org/W1565763308","https://openalex.org/W1593045043","https://openalex.org/W1823018422","https://openalex.org/W1933365859","https://openalex.org/W2015917093","https://openalex.org/W2047995599","https://openalex.org/W2061351603","https://openalex.org/W2087619920","https://openalex.org/W2094728533","https://openalex.org/W2098830640","https://openalex.org/W2099253769","https://openalex.org/W2107598941","https://openalex.org/W2120844411","https://openalex.org/W2123442489","https://openalex.org/W2126784811","https://openalex.org/W2132096166","https://openalex.org/W2134373401","https://openalex.org/W2141678623","https://openalex.org/W2144934730","https://openalex.org/W2145679919","https://openalex.org/W2148894869","https://openalex.org/W2151846280","https://openalex.org/W2152561112","https://openalex.org/W2156985047","https://openalex.org/W2157807817","https://openalex.org/W2176663335","https://openalex.org/W2177399422","https://openalex.org/W2250233410","https://openalex.org/W2250554077","https://openalex.org/W2251211017","https://openalex.org/W2251239360","https://openalex.org/W2251264718","https://openalex.org/W2251330961","https://openalex.org/W2251435463","https://openalex.org/W2252061787","https://openalex.org/W2252123671","https://openalex.org/W2293174806","https://openalex.org/W2294094610","https://openalex.org/W2296283641","https://openalex.org/W2406945108","https://openalex.org/W2463000881","https://openalex.org/W2514249165","https://openalex.org/W2573892686","https://openalex.org/W2574856563","https://openalex.org/W2803437449","https://openalex.org/W2806369456","https://openalex.org/W2886452452","https://openalex.org/W2963722184","https://openalex.org/W3031337294","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2082122846","https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W1569283511","https://openalex.org/W4298129735","https://openalex.org/W2385713529","https://openalex.org/W1850639582","https://openalex.org/W2599749361","https://openalex.org/W2949769632"],"abstract_inverted_index":{"The":[0],"ambitious":[1],"goal":[2,64],"of":[3,28,69],"this":[4,63],"work":[5],"is":[6,33,59],"to":[7,35,45,51,82],"develop":[8],"a":[9,24,40,67,145],"cross-lingual":[10],"name":[11,37,114],"tagging":[12,115],"and":[13,48,88,95,105,116,127,135],"linking":[14,117],"framework":[15,32],"for":[16,119,137],"282":[17,120,138],"languages":[18,84,121,139],"that":[19],"exist":[20],"in":[21,26],"Wikipedia.":[22],"Given":[23],"document":[25],"any":[27],"these":[29],"languages,":[30],"our":[31],"able":[34],"identify":[36],"mentions,":[38],"assign":[39],"coarse-grained":[41],"or":[42],"fine-grained":[43],"type":[44],"each":[46],"mention,":[47],"link":[49],"it":[50,58],"an":[52],"English":[53,81],"Knowledge":[54],"Base":[55],"(KB)":[56],"if":[57],"linkable.":[60],"We":[61],"achieve":[62],"by":[65,77],"performing":[66],"series":[68],"new":[70,146],"KB":[71,89],"mining":[72,106],"methods:":[73],"generating":[74],"\"silver-standard\"":[75],"annotations":[76,79,92],"transferring":[78],"from":[80,102,110],"other":[83],"through":[85,93],"crosslingual":[86,111],"links":[87],"properties,":[90],"refining":[91],"self-training":[94],"topic":[96],"selection,":[97],"deriving":[98],"language-specific":[99],"morphology":[100],"features":[101],"anchor":[103],"links,":[104],"word":[107],"translation":[108],"pairs":[109],"links.":[112],"Both":[113],"results":[118],"are":[122,140],"promising":[123],"on":[124],"Wikipedia":[125],"data":[126,132],"on-Wikipedia":[128],"data.":[129],"All":[130],"the":[131],"sets,":[133],"resources":[134],"systems":[136],"made":[141],"publicly":[142],"available":[143],"as":[144],"benchmark":[147],"1":[148],".":[149]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":80},{"year":2022,"cited_by_count":64},{"year":2021,"cited_by_count":60},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}