{"id":"https://openalex.org/W2435130738","doi":"https://doi.org/10.1017/s1351324916000152","title":"Building and using multimodal comparable corpora for machine translation","display_name":"Building and using multimodal comparable corpora for machine translation","publication_year":2016,"publication_date":"2016-06-15","ids":{"openalex":"https://openalex.org/W2435130738","doi":"https://doi.org/10.1017/s1351324916000152","mag":"2435130738"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324916000152","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324916000152","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","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/A5046400614","display_name":"Haithem Afli","orcid":"https://orcid.org/0000-0002-7449-4707"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"HAITHEM AFLI","raw_affiliation_strings":["Universit\u00e9 du Maine, Avenue Olivier Messiaen F-72085 - LE MANS, France e-mails:"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 du Maine, Avenue Olivier Messiaen F-72085 - LE MANS, France e-mails:","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043289060","display_name":"Lo\u00efc Barrault","orcid":"https://orcid.org/0000-0002-0634-6147"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"LO\u00cfC BARRAULT","raw_affiliation_strings":["Universit\u00e9 du Maine, Avenue Olivier Messiaen F-72085 - LE MANS, France e-mails:"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 du Maine, Avenue Olivier Messiaen F-72085 - LE MANS, France e-mails:","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015857371","display_name":"Holger Schwenk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"HOLGER SCHWENK","raw_affiliation_strings":["Universit\u00e9 du Maine, Avenue Olivier Messiaen F-72085 - LE MANS, France e-mails:"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 du Maine, Avenue Olivier Messiaen F-72085 - LE MANS, France e-mails:","institution_ids":["https://openalex.org/I4210108471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046400614"],"corresponding_institution_ids":["https://openalex.org/I4210108471"],"apc_list":null,"apc_paid":null,"fwci":1.7736,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.891826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"22","issue":"4","first_page":"603","last_page":"625"},"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.9346256256103516},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8510546684265137},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7066222429275513},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6960105895996094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6474745869636536},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6022952795028687},{"id":"https://openalex.org/keywords/economic-shortage","display_name":"Economic shortage","score":0.5220708250999451},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5034307837486267},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.4460486173629761},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.44379723072052},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.4402429461479187},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.41486990451812744},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3608276844024658},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3354684114456177},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06956687569618225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9346256256103516},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8510546684265137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7066222429275513},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6960105895996094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6474745869636536},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6022952795028687},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.5220708250999451},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5034307837486267},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.4460486173629761},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.44379723072052},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4402429461479187},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.41486990451812744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3608276844024658},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3354684114456177},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06956687569618225},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s1351324916000152","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324916000152","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01433195v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01433195","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","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":"Journal of Natural Language Engineering, 2015","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"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":31,"referenced_works":["https://openalex.org/W11209375","https://openalex.org/W75158669","https://openalex.org/W92412080","https://openalex.org/W177378321","https://openalex.org/W1494864219","https://openalex.org/W1631260214","https://openalex.org/W1988012253","https://openalex.org/W2006969979","https://openalex.org/W2047295649","https://openalex.org/W2065565011","https://openalex.org/W2080373976","https://openalex.org/W2100240599","https://openalex.org/W2101105183","https://openalex.org/W2101456909","https://openalex.org/W2104103102","https://openalex.org/W2104401056","https://openalex.org/W2107695330","https://openalex.org/W2124807415","https://openalex.org/W2140903445","https://openalex.org/W2149327368","https://openalex.org/W2153653739","https://openalex.org/W2159948109","https://openalex.org/W2166098990","https://openalex.org/W2250357346","https://openalex.org/W2407127455","https://openalex.org/W2407996486","https://openalex.org/W4241645538","https://openalex.org/W6652311901","https://openalex.org/W6714050621","https://openalex.org/W6714081051","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2099607809","https://openalex.org/W2518299649","https://openalex.org/W2395641992","https://openalex.org/W2807475932","https://openalex.org/W3021126373","https://openalex.org/W1915251500","https://openalex.org/W4280571180","https://openalex.org/W3066373881","https://openalex.org/W3175595715","https://openalex.org/W3152052241"],"abstract_inverted_index":{"Abstract":[0],"In":[1,49],"recent":[2],"decades,":[3],"statistical":[4,106],"approaches":[5],"have":[6,35],"significantly":[7],"advanced":[8],"the":[9,16,24,44,121,132,135],"development":[10],"of":[11,18,26,30,46,134],"machine":[12,107],"translation":[13,108,143],"systems.":[14],"However,":[15],"applicability":[17],"these":[19],"methods":[20],"directly":[21],"depends":[22],"on":[23,138],"availability":[25],"very":[27],"large":[28,117],"quantities":[29],"parallel":[31,47,66,128],"data.":[32],"Recent":[33],"works":[34],"demonstrated":[36],"that":[37],"a":[38,68,104,116,150],"comparable":[39,57,70],"corpus":[40,71,119],"can":[41],"compensate":[42],"for":[43,64],"shortage":[45],"corpora.":[48],"this":[50],"paper,":[51],"we":[52],"propose":[53],"an":[54,96,139],"alternative":[55],"to":[56,126,141],"corpora":[58],"containing":[59],"text":[60,79,118],"documents":[61,74],"as":[62],"resources":[63],"extracting":[65],"data:":[67],"multimodal":[69],"with":[72,103],"audio":[73,92],"in":[75,81,115,120,124],"source":[76],"language":[77,123],"and":[78,87,101,145],"document":[80],"target":[82,122],"language,":[83],"built":[84],"from":[85],"Euronews":[86],"TED":[88],"web":[89],"sites.":[90],"The":[91],"is":[93],"transcribed":[94],"by":[95],"automatic":[97],"speech":[98],"recognition":[99],"system,":[100],"translated":[102],"baseline":[105],"system.":[109],"We":[110,130],"then":[111],"use":[112],"information":[113],"retrieval":[114],"order":[125],"extract":[127],"sentences/phrases.":[129],"evaluate":[131],"quality":[133],"extracted":[136],"data":[137],"English":[140],"French":[142],"task":[144],"show":[146],"significant":[147],"improvements":[148],"over":[149],"state-of-the-art":[151],"baseline.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
