{"id":"https://openalex.org/W4413133986","doi":"https://doi.org/10.1007/s10579-025-09854-z","title":"TANDO+: corpus and baselines for document-level machine translation in Basque\u2013Spanish and Basque\u2013French","display_name":"TANDO+: corpus and baselines for document-level machine translation in Basque\u2013Spanish and Basque\u2013French","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413133986","doi":"https://doi.org/10.1007/s10579-025-09854-z"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-025-09854-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09854-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09854-z.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09854-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045548213","display_name":"Harritxu Gete","orcid":null},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Harritxu Gete","raw_affiliation_strings":["Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), University of the Basque Country (UPV/EHU), Leioa, Spain"],"affiliations":[{"raw_affiliation_string":"Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), University of the Basque Country (UPV/EHU), Leioa, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087412588","display_name":"Thierry Etchegoyhen","orcid":"https://orcid.org/0000-0001-7253-1693"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Thierry Etchegoyhen","raw_affiliation_strings":["Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), Donostia-San Sebasti\u00e1n, Spain"],"affiliations":[{"raw_affiliation_string":"Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), Donostia-San Sebasti\u00e1n, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037338094","display_name":"Gorka Labaka","orcid":"https://orcid.org/0000-0003-4611-2502"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Gorka Labaka","raw_affiliation_strings":["HiTZ Center - Ixa, University of the Basque Country (UPV/EHU), Donostia-San Sebasti\u00e1n, Spain"],"affiliations":[{"raw_affiliation_string":"HiTZ Center - Ixa, University of the Basque Country (UPV/EHU), Donostia-San Sebasti\u00e1n, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035960421","display_name":"Ander Corral","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097299","display_name":"MP Technologies (United States)","ror":"https://ror.org/00t6eqy44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210097299"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ander Corral","raw_affiliation_strings":["Orai NLP Technologies, Usurbil, Spain"],"affiliations":[{"raw_affiliation_string":"Orai NLP Technologies, Usurbil, Spain","institution_ids":["https://openalex.org/I4210097299"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067981207","display_name":"Xabier Saralegi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097299","display_name":"MP Technologies (United States)","ror":"https://ror.org/00t6eqy44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210097299"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xabier Saralegi","raw_affiliation_strings":["Orai NLP Technologies, Usurbil, Spain"],"affiliations":[{"raw_affiliation_string":"Orai NLP Technologies, Usurbil, Spain","institution_ids":["https://openalex.org/I4210097299"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017683091","display_name":"Nora Aranberri","orcid":"https://orcid.org/0000-0003-3719-9167"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nora Aranberri","raw_affiliation_strings":["HiTZ Center - Ixa, University of the Basque Country (UPV/EHU), Donostia-San Sebasti\u00e1n, Spain"],"affiliations":[{"raw_affiliation_string":"HiTZ Center - Ixa, University of the Basque Country (UPV/EHU), Donostia-San Sebasti\u00e1n, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003344157","display_name":"David Ponce","orcid":"https://orcid.org/0000-0002-6756-2441"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Ponce","raw_affiliation_strings":["Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), University of the Basque Country (UPV/EHU), Leioa, Spain"],"affiliations":[{"raw_affiliation_string":"Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), University of the Basque Country (UPV/EHU), Leioa, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022233627","display_name":"Igor Ellakuria Santos","orcid":null},"institutions":[{"id":"https://openalex.org/I162361429","display_name":"Mondragon Unibertsitatea","ror":"https://ror.org/00wvqgd19","country_code":"ES","type":"education","lineage":["https://openalex.org/I162361429"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Igor Ellakuria Santos","raw_affiliation_strings":["ISEA, Arrasate-Mondrag\u00f3n, Spain"],"affiliations":[{"raw_affiliation_string":"ISEA, Arrasate-Mondrag\u00f3n, Spain","institution_ids":["https://openalex.org/I162361429"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110733682","display_name":"Maite Mart\u00edn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149851","display_name":"Hero Espa\u00f1a (Spain)","ror":"https://ror.org/03s1jks46","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210149851"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Maite Martin","raw_affiliation_strings":["Ametzagai\u00f1a, Hernani, Spain"],"affiliations":[{"raw_affiliation_string":"Ametzagai\u00f1a, Hernani, Spain","institution_ids":["https://openalex.org/I4210149851"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5045548213"],"corresponding_institution_ids":["https://openalex.org/I169108374"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11591206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"59","issue":"4","first_page":"3699","last_page":"3739"},"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":0.9998000264167786,"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":0.9973999857902527,"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":0.8483957052230835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8308162689208984},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.762121319770813},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7072139382362366},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6448493599891663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6426830291748047},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6118218898773193},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.420957088470459},{"id":"https://openalex.org/keywords/evaluation-of-machine-translation","display_name":"Evaluation of machine translation","score":0.4101809859275818},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.24203991889953613},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.19422227144241333},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07214409112930298}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8483957052230835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308162689208984},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.762121319770813},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7072139382362366},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6448493599891663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6426830291748047},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6118218898773193},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.420957088470459},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.4101809859275818},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.24203991889953613},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.19422227144241333},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07214409112930298},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10579-025-09854-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09854-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09854-z.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10579-025-09854-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09854-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09854-z.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321705","display_name":"Eusko Jaurlaritza","ror":"https://ror.org/00pz2fp31"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413133986.pdf","grobid_xml":"https://content.openalex.org/works/W4413133986.grobid-xml"},"referenced_works_count":93,"referenced_works":["https://openalex.org/W131501223","https://openalex.org/W222053410","https://openalex.org/W255975419","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2136353104","https://openalex.org/W2163038970","https://openalex.org/W2166545452","https://openalex.org/W2250342921","https://openalex.org/W2419539795","https://openalex.org/W2513660799","https://openalex.org/W2579327808","https://openalex.org/W2741788241","https://openalex.org/W2759173152","https://openalex.org/W2759511005","https://openalex.org/W2767019613","https://openalex.org/W2786828416","https://openalex.org/W2799051177","https://openalex.org/W2806987872","https://openalex.org/W2885588803","https://openalex.org/W2888159079","https://openalex.org/W2891534142","https://openalex.org/W2922158773","https://openalex.org/W2941700260","https://openalex.org/W2952446148","https://openalex.org/W2962712961","https://openalex.org/W2962784628","https://openalex.org/W2962802109","https://openalex.org/W2962826395","https://openalex.org/W2962943802","https://openalex.org/W2963212250","https://openalex.org/W2963532001","https://openalex.org/W2964093087","https://openalex.org/W2964120396","https://openalex.org/W2964202354","https://openalex.org/W2964289193","https://openalex.org/W2964291396","https://openalex.org/W2964343359","https://openalex.org/W2970279348","https://openalex.org/W2970529093","https://openalex.org/W2970797723","https://openalex.org/W2971278086","https://openalex.org/W2971347700","https://openalex.org/W2977772147","https://openalex.org/W2983108239","https://openalex.org/W2984500026","https://openalex.org/W2989066524","https://openalex.org/W3029849870","https://openalex.org/W3031596474","https://openalex.org/W3035520602","https://openalex.org/W3035629723","https://openalex.org/W3046644997","https://openalex.org/W3093404841","https://openalex.org/W3093559770","https://openalex.org/W3100806282","https://openalex.org/W3101683892","https://openalex.org/W3102507836","https://openalex.org/W3105214104","https://openalex.org/W3116490761","https://openalex.org/W3176626464","https://openalex.org/W3198554029","https://openalex.org/W3202612196","https://openalex.org/W3203909556","https://openalex.org/W4205862160","https://openalex.org/W4205902821","https://openalex.org/W4206027098","https://openalex.org/W4210636016","https://openalex.org/W4229853184","https://openalex.org/W4285121328","https://openalex.org/W4298050700","https://openalex.org/W4321472057","https://openalex.org/W4364387438","https://openalex.org/W4365802915","https://openalex.org/W4367061074","https://openalex.org/W4384918448","https://openalex.org/W4385565605","https://openalex.org/W4385570335","https://openalex.org/W4385822323","https://openalex.org/W4389519421","https://openalex.org/W4389520065","https://openalex.org/W4389524029","https://openalex.org/W4402684074","https://openalex.org/W4402684243","https://openalex.org/W4404689873","https://openalex.org/W4411113428","https://openalex.org/W4411630291","https://openalex.org/W6631190155","https://openalex.org/W6691173707","https://openalex.org/W6739901393","https://openalex.org/W6779502067","https://openalex.org/W6781389758","https://openalex.org/W6796581206","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W3151736118","https://openalex.org/W3097971125","https://openalex.org/W2962780935","https://openalex.org/W4387490002","https://openalex.org/W2169279899","https://openalex.org/W2026303297","https://openalex.org/W2532807140","https://openalex.org/W3196981096","https://openalex.org/W2395826315","https://openalex.org/W2883671469"],"abstract_inverted_index":{"Context-aware":[0],"Neural":[1],"Machine":[2],"Translation":[3],"can":[4],"potentially":[5],"enhance":[6],"automated":[7],"translation":[8,142],"quality":[9],"through":[10],"effective":[11],"modelling":[12,24],"of":[13,37,65,107],"context":[14],"beyond":[15],"the":[16,33,53,74,132,145],"sentence":[17],"level.":[18],"However,":[19],"suitable":[20],"corpora":[21],"for":[22,32,52,101,104,144],"contextual":[23,111,124],"are":[25],"still":[26],"scarce,":[27],"presenting":[28],"a":[29,49,62],"significant":[30],"challenge":[31],"training":[34],"and":[35,58,87,89,109,116,121,128,138],"evaluation":[36],"context-aware":[38,140],"systems.":[39],"To":[40],"address":[41],"this":[42,66],"challenge,":[43],"we":[44,114],"describe":[45],"tando":[46],"$${}^{+}$$":[47],",":[48],"document-level":[50],"corpus":[51,78,133],"under-resourced":[54,148],"language":[55,149],"pairs":[56],"Basque-French":[57],"Basque-Spanish.":[59],"We":[60],"provide":[61],"detailed":[63],"description":[64],"corpus,":[67],"which":[68],"is":[69,134],"to":[70,136],"be":[71],"shared":[72],"with":[73],"scientific":[75],"community.":[76],"The":[77],"comprises":[79],"parallel":[80],"data":[81],"from":[82],"diverse":[83],"domains":[84],"(literature,":[85],"subtitles,":[86],"news)":[88],"incorporates":[90],"context-level":[91],"information.":[92],"Additionally,":[93,113],"it":[94],"provides":[95],"manually":[96],"crafted":[97],"contrastive":[98],"test":[99],"sets":[100],"Basque-Spanish,":[102],"designed":[103],"comprehensive":[105],"assessment":[106],"gender":[108],"register":[110],"phenomena.":[112],"train":[115,137],"evaluate":[117,139],"sentence-level":[118],"baseline":[119],"models":[120],"several":[122],"state-of-the-art":[123],"variants.":[125],"Our":[126],"results":[127],"analyses":[129],"indicate":[130],"that":[131],"well-suited":[135],"machine":[141],"systems":[143],"two":[146],"selected":[147],"pairs.":[150]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}