{"id":"https://openalex.org/W2769651303","doi":"https://doi.org/10.1162/tacl_a_00075","title":"Phrase Table Induction Using In-Domain Monolingual Data for Domain Adaptation in Statistical Machine Translation","display_name":"Phrase Table Induction Using In-Domain Monolingual Data for Domain Adaptation in Statistical Machine Translation","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2769651303","doi":"https://doi.org/10.1162/tacl_a_00075","mag":"2769651303"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00075","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00075","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00075","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00075","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072172103","display_name":"Benjamin Marie","orcid":"https://orcid.org/0000-0001-9880-5541"},"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, 3-5                         Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan,","National Institute of Information and Communications Technology, 3-5\n Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, 3-5                         Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan,","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, 3-5\n Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, 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":true,"raw_author_name":"Atsushi Fujita","raw_affiliation_strings":["National Institute of Information and Communications Technology, 3-5                         Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan,","National Institute of Information and Communications Technology, 3-5\n Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, 3-5                         Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan,","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, 3-5\n Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0289, Japan,","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072172103","https://openalex.org/A5101988321"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.2081,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65912805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"487","last_page":"500"},"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":0.9994999766349792,"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/T13629","display_name":"Text Readability and Simplification","score":0.986299991607666,"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":0.8725979328155518},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8300914168357849},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6639649868011475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.645248293876648},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.637263834476471},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.580218493938446},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.48257508873939514},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4636261463165283},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37903064489364624},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08682477474212646}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8725979328155518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300914168357849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6639649868011475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.645248293876648},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.637263834476471},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.580218493938446},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.48257508873939514},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4636261463165283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37903064489364624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08682477474212646},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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":2,"locations":[{"id":"doi:10.1162/tacl_a_00075","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00075","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00075","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a508c20554eb49c5bedc05d9c8834ce6","is_oa":false,"landing_page_url":"https://doaj.org/article/a508c20554eb49c5bedc05d9c8834ce6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 5 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00075","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00075","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00075","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2769651303.pdf","grobid_xml":"https://content.openalex.org/works/W2769651303.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W38126138","https://openalex.org/W342285082","https://openalex.org/W1626233182","https://openalex.org/W1828724394","https://openalex.org/W1905522558","https://openalex.org/W1984052055","https://openalex.org/W2101105183","https://openalex.org/W2103042430","https://openalex.org/W2104103102","https://openalex.org/W2107695330","https://openalex.org/W2113199498","https://openalex.org/W2117198860","https://openalex.org/W2121415745","https://openalex.org/W2121745180","https://openalex.org/W2124807415","https://openalex.org/W2126725946","https://openalex.org/W2133280805","https://openalex.org/W2133459682","https://openalex.org/W2139812240","https://openalex.org/W2140406733","https://openalex.org/W2144600658","https://openalex.org/W2145662801","https://openalex.org/W2153579005","https://openalex.org/W2158199200","https://openalex.org/W2159755860","https://openalex.org/W2165630967","https://openalex.org/W2166098990","https://openalex.org/W2169360026","https://openalex.org/W2172268343","https://openalex.org/W2185701500","https://openalex.org/W2250229103","https://openalex.org/W2250952810","https://openalex.org/W2251939518","https://openalex.org/W2293547632","https://openalex.org/W2425903306","https://openalex.org/W2431681589","https://openalex.org/W2508069829","https://openalex.org/W2576482813","https://openalex.org/W2963002901","https://openalex.org/W2963813556","https://openalex.org/W2963915291"],"related_works":["https://openalex.org/W2384400852","https://openalex.org/W2963259630","https://openalex.org/W3204898214","https://openalex.org/W2765271678","https://openalex.org/W2070920720","https://openalex.org/W2122294272","https://openalex.org/W2398549619","https://openalex.org/W1542743110","https://openalex.org/W2728761353","https://openalex.org/W2883671469"],"abstract_inverted_index":{"We":[0,84,113],"present":[1],"a":[2,21,73,103],"new":[3],"framework":[4],"to":[5,19,27,78,139],"induce":[6,79],"an":[7,80,109,116],"in-domain":[8,12,81,110],"phrase":[9,47,57,67,82,123],"table":[10],"from":[11],"monolingual":[13],"data":[14,137],"that":[15,107,119],"can":[16],"be":[17],"used":[18,138],"adapt":[20],"general-domain":[22,142],"statistical":[23],"machine":[24],"translation":[25,92],"system":[26,106],"the":[28,51,55,87,121,135,141],"targeted":[29],"domain.":[30],"Our":[31],"method":[32],"first":[33],"compiles":[34],"sets":[35],"of":[36,54],"phrases":[37,132],"in":[38,76,94,134],"source":[39],"and":[40,44,69,97,131],"target":[41],"languages":[42],"separately":[43],"generates":[45],"candidate":[46,66],"pairs":[48],"by":[49],"taking":[50],"Cartesian":[52],"product":[53],"two":[56,95],"sets.":[58],"It":[59],"then":[60],"computes":[61],"inexpensive":[62],"features":[63],"for":[64,129],"each":[65],"pair":[68,89],"filters":[70],"them":[71],"using":[72],"supervised":[74],"classifier":[75],"order":[77],"table.":[83],"experimented":[85],"on":[86],"language":[88],"English\u2013French,":[90],"both":[91],"directions,":[93],"domains":[96],"obtained":[98],"consistently":[99],"better":[100],"results":[101],"than":[102],"strong":[104],"baseline":[105,143],"uses":[108],"bilingual":[111],"lexicon.":[112],"also":[114],"conducted":[115],"error":[117],"analysis":[118],"showed":[120],"induced":[122],"tables":[124],"proposed":[125],"useful":[126],"translations,":[127],"especially":[128],"words":[130],"unseen":[133],"parallel":[136],"train":[140],"system.":[144]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}