{"id":"https://openalex.org/W2947288950","doi":"https://doi.org/10.1007/s10579-020-09514-4","title":"DiaBLa: a corpus of bilingual spontaneous written dialogues for machine translation","display_name":"DiaBLa: a corpus of bilingual spontaneous written dialogues for machine translation","publication_year":2020,"publication_date":"2020-11-23","ids":{"openalex":"https://openalex.org/W2947288950","doi":"https://doi.org/10.1007/s10579-020-09514-4","mag":"2947288950"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-020-09514-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-020-09514-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-020-09514-4.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-020-09514-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046431394","display_name":"Rachel Bawden","orcid":"https://orcid.org/0000-0001-9553-1768"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rachel Bawden","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, Scotland, UK"],"raw_orcid":"https://orcid.org/0000-0001-9553-1768","affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, Scotland, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085230943","display_name":"\u00c9ric Bilinski","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Eric Bilinski","raw_affiliation_strings":["LIMSI, CNRS, Universit\u00e9 Paris-Saclay, Orsay, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI, CNRS, Universit\u00e9 Paris-Saclay, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774746","display_name":"Thomas Lavergne","orcid":"https://orcid.org/0000-0002-9498-4551"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Lavergne","raw_affiliation_strings":["LIMSI, CNRS, Universit\u00e9 Paris-Saclay, Univ.\u00a0Paris-Sud, Orsay, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI, CNRS, Universit\u00e9 Paris-Saclay, Univ.\u00a0Paris-Sud, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I277688954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001616788","display_name":"Sophie Rosset","orcid":"https://orcid.org/0000-0002-6865-4989"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sophie Rosset","raw_affiliation_strings":["LIMSI, CNRS, Universit\u00e9 Paris-Saclay, Orsay, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI, CNRS, Universit\u00e9 Paris-Saclay, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210115485"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.5363,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72982405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"55","issue":"3","first_page":"635","last_page":"660"},"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":0.9994000196456909,"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":0.9986000061035156,"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/machine-translation","display_name":"Machine translation","score":0.6820025444030762},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6817346215248108},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6756905913352966},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6291882395744324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6269618272781372},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6205668449401855},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5401159524917603},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5064512491226196},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4370276927947998},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4362753629684448},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4358874559402466},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41838011145591736},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05382603406906128}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6820025444030762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6817346215248108},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6756905913352966},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6291882395744324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6269618272781372},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6205668449401855},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5401159524917603},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5064512491226196},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4370276927947998},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4362753629684448},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4358874559402466},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41838011145591736},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05382603406906128},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s10579-020-09514-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-020-09514-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-020-09514-4.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1905.13354","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.13354","pdf_url":"https://arxiv.org/pdf/1905.13354","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2947288950","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.13354v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:HAL:hal-03021633v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-03021633","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation, 2020, 55, pp.635-660. &#x27E8;10.1007/s10579-020-09514-4&#x27E9;","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.1905.13354","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.13354","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1007/s10579-020-09514-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-020-09514-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-020-09514-4.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320332","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90"},{"id":"https://openalex.org/F4320335899","display_name":"Sciences et Technologies de l'information et de la Communication, Universit\u00e9 Paris-Saclay","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947288950.pdf","grobid_xml":"https://content.openalex.org/works/W2947288950.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W37344644","https://openalex.org/W229329885","https://openalex.org/W1502890786","https://openalex.org/W2060377713","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2132474591","https://openalex.org/W2133564696","https://openalex.org/W2148708890","https://openalex.org/W2290195878","https://openalex.org/W2400103538","https://openalex.org/W2419539795","https://openalex.org/W2467834614","https://openalex.org/W2572044271","https://openalex.org/W2577267675","https://openalex.org/W2594229957","https://openalex.org/W2795467683","https://openalex.org/W2806412155","https://openalex.org/W2962784628","https://openalex.org/W2962802109","https://openalex.org/W2964130895","https://openalex.org/W2964291396","https://openalex.org/W2964308564","https://openalex.org/W2964343359"],"related_works":["https://openalex.org/W3108362930","https://openalex.org/W2245425211","https://openalex.org/W3138669164","https://openalex.org/W2895531002","https://openalex.org/W2895201082","https://openalex.org/W2103066065","https://openalex.org/W3020598644","https://openalex.org/W2222540224","https://openalex.org/W17742173","https://openalex.org/W2024626425","https://openalex.org/W2243092139","https://openalex.org/W2112997175","https://openalex.org/W2394756230","https://openalex.org/W3133996924","https://openalex.org/W343516559","https://openalex.org/W2874934353","https://openalex.org/W2949736311","https://openalex.org/W2966599707","https://openalex.org/W565900286","https://openalex.org/W2734287438"],"abstract_inverted_index":{"Abstract":[0],"We":[1,106],"present":[2],"a":[3,43,76,89,98],"new":[4],"English\u2013French":[5],"dataset":[6],"for":[7,14,81,92,100],"the":[8,61,82,101,112,117,127],"evaluation":[9],"of":[10,37,45,56,103,111],"Machine":[11],"Translation":[12],"(MT)":[13],"informal,":[15],"written":[16],"bilingual":[17],"dialogue.":[18],"The":[19,48,79],"test":[20],"set":[21],"contains":[22],"144":[23],"spontaneous":[24],"dialogues":[25,49],"(5700+":[26],"sentences)":[27],"between":[28,126],"native":[29],"English":[30],"and":[31,72,96],"French":[32],"speakers,":[33],"mediated":[34],"by":[35,52,60,68],"one":[36],"two":[38,128],"neural":[39],"MT":[40,57,94,124,129],"systems":[41,130],"in":[42,123],"range":[44],"role-play":[46],"settings.":[47],"are":[50],"accompanied":[51],"fine-grained":[53],"sentence-level":[54],"judgments":[55,119],"quality,":[58],"produced":[59,75],"dialogue":[62],"participants":[63],"themselves,":[64],"as":[65,67],"well":[66],"manually":[69],"normalised":[70],"versions":[71],"reference":[73],"translations":[74],"posteriori":[77],".":[78],"motivation":[80],"corpus":[83,99,113],"is":[84],"twofold:":[85],"to":[86,114],"provide":[87,107],"(i)":[88],"unique":[90],"resource":[91],"evaluating":[93],"models,":[95],"(ii)":[97],"analysis":[102,110],"MT-mediated":[104],"communication.":[105],"an":[108],"initial":[109],"confirm":[115],"that":[116],"participants\u2019":[118],"reveal":[120],"perceptible":[121],"differences":[122],"quality":[125],"used.":[131]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
