{"id":"https://openalex.org/W2603776682","doi":"https://doi.org/10.1145/3003726","title":"Inducing a Bilingual Lexicon from Short Parallel Multiword Sequences","display_name":"Inducing a Bilingual Lexicon from Short Parallel Multiword Sequences","publication_year":2017,"publication_date":"2017-03-17","ids":{"openalex":"https://openalex.org/W2603776682","doi":"https://doi.org/10.1145/3003726","mag":"2603776682"},"language":"en","primary_location":{"id":"doi:10.1145/3003726","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3003726","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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 and Low-Resource 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/A5081198426","display_name":"Andrew Finch","orcid":"https://orcid.org/0000-0002-7067-7098"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Andrew Finch","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049029124","display_name":"Taisuke Harada","orcid":"https://orcid.org/0000-0003-0468-2777"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taisuke Harada","raw_affiliation_strings":["Kyushu University, Fukuoka City, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University, Fukuoka City, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073822077","display_name":"Kumiko Tanaka\u2010Ishii","orcid":"https://orcid.org/0000-0003-1752-3951"},"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":"Kumiko Tanaka-Ishii","raw_affiliation_strings":["University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033318800","display_name":"Eiichiro Sumita","orcid":"https://orcid.org/0000-0002-1028-4399"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eiichiro Sumita","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3988,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69554972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"16","issue":"3","first_page":"1","last_page":"20"},"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":0.9976999759674072,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8580327033996582},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7021945118904114},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6817164421081543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6797924041748047},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4862152636051178},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.4840768873691559},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.46069642901420593},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4533230662345886},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4514613747596741},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4452645182609558},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43923404812812805},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3795093297958374},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3155771493911743},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10395267605781555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8580327033996582},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7021945118904114},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6817164421081543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6797924041748047},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4862152636051178},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.4840768873691559},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.46069642901420593},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4533230662345886},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4514613747596741},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4452645182609558},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43923404812812805},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3795093297958374},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3155771493911743},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10395267605781555},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3003726","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3003726","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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 and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W12911848","https://openalex.org/W1539673959","https://openalex.org/W1683241483","https://openalex.org/W1700952868","https://openalex.org/W1763771263","https://openalex.org/W1777547826","https://openalex.org/W2043454835","https://openalex.org/W2087309226","https://openalex.org/W2102443632","https://openalex.org/W2122228338","https://openalex.org/W2126270798","https://openalex.org/W2133444727","https://openalex.org/W2140991203","https://openalex.org/W2146853049","https://openalex.org/W2150507172","https://openalex.org/W2156985047","https://openalex.org/W2164626326","https://openalex.org/W2186379673","https://openalex.org/W2252038832","https://openalex.org/W2400050865","https://openalex.org/W2541297210","https://openalex.org/W2578027111","https://openalex.org/W2594706607","https://openalex.org/W2759181158","https://openalex.org/W2912273839"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2951061418","https://openalex.org/W2804033347","https://openalex.org/W2157136552","https://openalex.org/W1538473846","https://openalex.org/W2773845044","https://openalex.org/W2420187884","https://openalex.org/W1978843799","https://openalex.org/W4307536116","https://openalex.org/W2603776682"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"a":[3,19,23,35,43,169],"technique":[4,17],"for":[5],"mining":[6,96,108,151],"bilingual":[7,44,189],"lexicons":[8],"from":[9,22],"pairs":[10,64,104,191],"of":[11,25,29,61,72,95,109,120,136,141,195],"parallel":[12],"short":[13],"word":[14,122,125,190],"sequences.":[15],"The":[16,32,48,67,115],"builds":[18],"generative":[20],"model":[21,33,39,49,69,116],"corpus":[24],"training":[26],"data":[27],"consisting":[28],"such":[30],"pairs.":[31],"is":[34,56,70,92,117,133,185],"hierarchical":[36],"nonparametric":[37],"Bayesian":[38],"that":[40,172,181],"directly":[41],"induces":[42],"lexicon":[45],"while":[46],"training.":[47],"learns":[50],"in":[51,112,138],"an":[52],"unsupervised":[53],"manner":[54],"and":[55,79,98,124,131,156,160,197],"designed":[57],"to":[58,105,165,187],"exploit":[59],"characteristics":[60],"the":[62,83,88,107,128,139,162,182,200],"language":[63,158],"being":[65],"mined.":[66],"proposed":[68,163,183],"capable":[71,94,119,135],"utilizing":[73],"commonly":[74],"used":[75],"word-pair":[76,175],"frequency":[77,176],"information":[78],"additionally":[80],"can":[81,99],"employ":[82],"internal":[84],"character":[85],"alignments":[86],"within":[87],"words":[89,111],"themselves.":[90],"It":[91],"thereby":[93],"transliterations":[97],"use":[100,173],"reliably":[101],"aligned":[102],"transliteration":[103],"support":[106],"other":[110],"their":[113],"context.":[114],"also":[118],"performing":[121],"reordering":[123],"deletion":[126],"during":[127],"alignment":[129],"process,":[130],"it":[132],"furthermore":[134],"operating":[137],"absence":[140],"full":[142],"segmentation":[143],"information.":[144,177],"In":[145],"this":[146],"work,":[147],"we":[148],"study":[149],"two":[150],"tasks":[152],"based":[153,167],"on":[154,168],"English-Japanese":[155],"English-Chinese":[157],"pairs,":[159],"compare":[161],"approach":[164],"baselines":[166],"simpler":[170],"models":[171],"only":[174],"Our":[178],"results":[179],"show":[180],"method":[184],"able":[186],"mine":[188],"at":[192],"higher":[193],"levels":[194],"precision":[196],"recall":[198],"than":[199],"baselines.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}