{"id":"https://openalex.org/W2074244346","doi":"https://doi.org/10.1145/2184436.2184439","title":"Statistical Extraction and Comparison of Pivot Words for Bilingual Lexicon Extension","display_name":"Statistical Extraction and Comparison of Pivot Words for Bilingual Lexicon Extension","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2074244346","doi":"https://doi.org/10.1145/2184436.2184439","mag":"2074244346"},"language":"en","primary_location":{"id":"doi:10.1145/2184436.2184439","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2184436.2184439","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","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/A5101506514","display_name":"Daniel Andrade","orcid":"https://orcid.org/0000-0002-1123-4369"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daniel Andrade","raw_affiliation_strings":["University of Tokyo","university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016823828","display_name":"Takuya Matsuzaki","orcid":"https://orcid.org/0000-0002-7425-4914"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Matsuzaki","raw_affiliation_strings":["University of Tokyo","university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112241147","display_name":"Jun\u2019ichi Tsujii","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun\u2019ichi Tsujii","raw_affiliation_strings":["University of Tokyo","university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.3048,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83820963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"11","issue":"2","first_page":"1","last_page":"31"},"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":0.9951000213623047,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8256860971450806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7925442457199097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7061548233032227},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.655762791633606},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5846498608589172},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5064500570297241},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4945773780345917},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.47950059175491333},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"Bilingual dictionary","score":0.47926661372184753},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4349316358566284},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2026805877685547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256860971450806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7925442457199097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7061548233032227},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.655762791633606},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5846498608589172},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5064500570297241},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4945773780345917},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.47950059175491333},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.47926661372184753},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4349316358566284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2026805877685547},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2184436.2184439","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2184436.2184439","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W71111251","https://openalex.org/W72471529","https://openalex.org/W111226416","https://openalex.org/W192665053","https://openalex.org/W1479719301","https://openalex.org/W1499293379","https://openalex.org/W1541966623","https://openalex.org/W1574901103","https://openalex.org/W1590839732","https://openalex.org/W1944231768","https://openalex.org/W1964707402","https://openalex.org/W1972871876","https://openalex.org/W1973550659","https://openalex.org/W2011248508","https://openalex.org/W2032442135","https://openalex.org/W2033314834","https://openalex.org/W2070900731","https://openalex.org/W2084277454","https://openalex.org/W2102749417","https://openalex.org/W2116410915","https://openalex.org/W2116780029","https://openalex.org/W2121415745","https://openalex.org/W2124810114","https://openalex.org/W2125290066","https://openalex.org/W2133837072","https://openalex.org/W2137057190","https://openalex.org/W2140406733","https://openalex.org/W2154558620","https://openalex.org/W2162967019","https://openalex.org/W2189289576","https://openalex.org/W2489487449","https://openalex.org/W2998237634","https://openalex.org/W4388319163"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W1585034923","https://openalex.org/W2167662847","https://openalex.org/W2922463763","https://openalex.org/W1527658996","https://openalex.org/W1978971213","https://openalex.org/W2511797247","https://openalex.org/W2252084125","https://openalex.org/W2270260950","https://openalex.org/W2947834980"],"abstract_inverted_index":{"Bilingual":[0],"dictionaries":[1],"can":[2],"be":[3,172],"automatically":[4],"extended":[5],"by":[6],"new":[7],"translations":[8],"using":[9,63,164],"comparable":[10,219],"corpora.":[11],"The":[12,66,183],"general":[13],"idea":[14],"is":[15,52,103],"based":[16,77],"on":[17,34,78],"the":[18,45,57,73,79,111,123,132,147,157,165,168,176,180,197,205,210,234,241,246],"assumption":[19],"that":[20,50,167,240],"similar":[21,24],"words":[22,96,98,139],"have":[23,31],"contexts":[25],"across":[26,140,220],"languages.":[27],"However,":[28],"previous":[29,254],"studies":[30],"mainly":[32],"focused":[33],"Indo-European":[35],"languages,":[36,227],"or":[37],"use":[38,118,229],"only":[39,56],"a":[40,82,101,107,119,153,161,191],"bag-of-words":[41,192],"model":[42],"to":[43,54,127,142,204,214,232,253],"describe":[44],"context.":[46,65],"Furthermore,":[47],"we":[48,90,117,135,228],"argue":[49],"it":[51],"helpful":[53],"extract":[55,91],"statistically":[58],"significant":[59],"context,":[60],"instead":[61],"of":[62,81,113,122,193,209,248],"all":[64],"present":[67],"approach":[68],"addresses":[69],"these":[70,137,216],"issues":[71],"in":[72,106],"following":[74],"manner.":[75],"First,":[76],"context":[80,188,217],"word":[83,159,178,249],"with":[84,202],"an":[85],"unknown":[86],"translation":[87,102,144,162,181],"(query":[88],"word),":[89],"salient":[92,114],"pivot":[93,115,138],"words.":[94],"Pivot":[95],"are":[97,225],"for":[99,146,174],"which":[100,224],"already":[104],"available":[105],"bilingual":[108],"dictionary.":[109],"For":[110],"extraction":[112],"words,":[116],"Bayesian":[120],"estimation":[121],"point-wise":[124],"mutual":[125],"information":[126],"measure":[128],"statistical":[129],"significance.":[130],"In":[131,212],"second":[133],"step,":[134],"match":[136],"languages":[141],"identify":[143],"candidates":[145],"query":[148,158,177],"word.":[149],"We":[150,238],"therefore":[151],"calculate":[152],"similarity":[154],"score":[155],"between":[156],"and":[160,179,196,200,222],"candidate":[163],"probability":[166],"same":[169],"pivots":[170],"will":[171],"extracted":[173],"both":[175],"candidate.":[182],"proposed":[184,242],"method":[185,243],"uses":[186],"several":[187,230],"positions,":[189],"namely,":[190],"one":[194],"sentence,":[195],"successors,":[198],"predecessors,":[199],"siblings":[201],"respect":[203],"dependency":[206,235],"parse":[207],"tree":[208],"sentence.":[211],"order":[213],"make":[215],"positions":[218],"Japanese":[221],"English,":[223],"unrelated":[226],"heuristics":[231],"adjust":[233],"trees":[236],"appropriately.":[237],"demonstrate":[239],"significantly":[244],"increases":[245],"accuracy":[247],"translations,":[250],"as":[251],"compared":[252],"methods.":[255]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}