{"id":"https://openalex.org/W2785381227","doi":"https://doi.org/10.1145/3168054","title":"Phrase Table Induction Using Monolingual Data for Low-Resource Statistical Machine Translation","display_name":"Phrase Table Induction Using Monolingual Data for Low-Resource Statistical Machine Translation","publication_year":2018,"publication_date":"2018-02-13","ids":{"openalex":"https://openalex.org/W2785381227","doi":"https://doi.org/10.1145/3168054","mag":"2785381227"},"language":"en","primary_location":{"id":"doi:10.1145/3168054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3168054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3168054","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":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3168054","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101488996","display_name":"Benjamin Marie","orcid":"https://orcid.org/0000-0002-5228-2762"},"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":true,"raw_author_name":"Benjamin Marie","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101988321","display_name":"Atsushi Fujita","orcid":"https://orcid.org/0000-0003-3799-8428"},"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":"Atsushi Fujita","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"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":2,"corresponding_author_ids":["https://openalex.org/A5101488996"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.9773,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81072726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"17","issue":"3","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9926999807357788,"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/phrase","display_name":"Phrase","score":0.9257569909095764},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8021594285964966},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6974980235099792},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6821582317352295},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6575143337249756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6504884958267212},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6278536319732666},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.5030991435050964},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.09841105341911316}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.9257569909095764},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021594285964966},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6974980235099792},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6821582317352295},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6575143337249756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6504884958267212},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6278536319732666},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.5030991435050964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.09841105341911316},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3168054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3168054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3168054","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":{"id":"doi:10.1145/3168054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3168054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3168054","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2785381227.pdf","grobid_xml":"https://content.openalex.org/works/W2785381227.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W38126138","https://openalex.org/W132913264","https://openalex.org/W1626233182","https://openalex.org/W1984052055","https://openalex.org/W2101105183","https://openalex.org/W2102616831","https://openalex.org/W2103042430","https://openalex.org/W2117198860","https://openalex.org/W2119727789","https://openalex.org/W2121415745","https://openalex.org/W2121745180","https://openalex.org/W2126725946","https://openalex.org/W2133280805","https://openalex.org/W2139812240","https://openalex.org/W2140406733","https://openalex.org/W2141440284","https://openalex.org/W2144600658","https://openalex.org/W2159755860","https://openalex.org/W2169360026","https://openalex.org/W2170204377","https://openalex.org/W2172268343","https://openalex.org/W2229725139","https://openalex.org/W2250229103","https://openalex.org/W2250952810","https://openalex.org/W2251939518","https://openalex.org/W2252212383","https://openalex.org/W2275683873","https://openalex.org/W2293547632","https://openalex.org/W2425903306","https://openalex.org/W2431681589","https://openalex.org/W2508069829","https://openalex.org/W2561995736","https://openalex.org/W2574531235","https://openalex.org/W2576306999","https://openalex.org/W2578511464","https://openalex.org/W2612649659","https://openalex.org/W2930957955","https://openalex.org/W2950133940","https://openalex.org/W2962795068","https://openalex.org/W2963002901","https://openalex.org/W2963506925","https://openalex.org/W2963915291","https://openalex.org/W2964334713","https://openalex.org/W3029251811"],"related_works":["https://openalex.org/W2566847733","https://openalex.org/W2122287718","https://openalex.org/W2010336863","https://openalex.org/W2740094425","https://openalex.org/W3204448004","https://openalex.org/W193726211","https://openalex.org/W2587602790","https://openalex.org/W3011059803","https://openalex.org/W2963259630","https://openalex.org/W2384400852"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,7,12,79,92,118,141,153],"new":[3],"method":[4,19,50,124,147],"for":[5,37,67],"inducing":[6],"phrase-based":[8],"translation":[9,109,128,135],"model":[10],"from":[11,62],"pair":[13],"of":[14,26,82,156],"unrelated":[15],"monolingual":[16,64,76,174],"corpora.":[17,47],"Our":[18],"is":[20,95],"able":[21],"to":[22,30,125,131,165],"deal":[23],"with":[24],"phrases":[25,59],"arbitrary":[27],"length":[28],"and":[29,57,78,91,107,169],"find":[31],"phrase":[32,52,69,87,93,100,119,142],"pairs":[33,53,88],"that":[34,116,140],"are":[35,89,176],"useful":[36,151],"statistical":[38],"machine":[39,127],"translation,":[40],"without":[41],"requiring":[42],"large":[43,132,166],"parallel":[44,83,167],"or":[45],"comparable":[46],"First,":[48],"our":[49,103,123,146],"generates":[51],"through":[54],"coupling":[55],"source":[56],"target":[58],"separately":[60],"collected":[61],"respective":[63],"data.":[65],"Then,":[66],"each":[68],"pair,":[70],"we":[71,114,138,161],"compute":[72],"features":[73],"using":[74,97],"the":[75,98,126],"data":[77],"small":[80,173],"quantity":[81],"sentences.":[84],"Finally,":[85],"incorrect":[86],"pruned,":[90],"table":[94,120,143],"made":[96],"remaining":[99],"pairs.":[101],"In":[102],"experiments":[104],"on":[105],"French--Japanese":[106],"Spanish--Japanese":[108],"tasks":[110],"under":[111],"low-resource":[112],"conditions,":[113],"observe":[115],"incorporating":[117],"induced":[121,144],"by":[122,145],"system":[129],"leads":[130],"improvements":[133],"in":[134,152],"quality.":[136],"Furthermore,":[137],"show":[139],"can":[148],"also":[149],"be":[150],"wide":[154],"range":[155],"configurations,":[157],"including":[158],"configurations":[159,170],"where":[160,171],"have":[162],"already":[163],"access":[164],"corpora":[168,175],"only":[172],"available.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}