{"id":"https://openalex.org/W4210636016","doi":"https://doi.org/10.1007/s10579-021-09572-2","title":"Making the most of comparable corpora in Neural Machine Translation: a case study","display_name":"Making the most of comparable corpora in Neural Machine Translation: a case study","publication_year":2022,"publication_date":"2022-01-27","ids":{"openalex":"https://openalex.org/W4210636016","doi":"https://doi.org/10.1007/s10579-021-09572-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-021-09572-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-021-09572-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-021-09572-2.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-021-09572-2.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"]},{"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":true,"raw_author_name":"Harritxu Gete","raw_affiliation_strings":["University of the Basque Country (UPV/EHU), Leioa, Bizkaia, Spain","Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), Donostia/San Sebasti\u00e1n, Gipuzkoa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Basque Country (UPV/EHU), Leioa, Bizkaia, Spain","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), Donostia/San Sebasti\u00e1n, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"last","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, Gipuzkoa, Spain"],"raw_orcid":"https://orcid.org/0000-0001-7253-1693","affiliations":[{"raw_affiliation_string":"Vicomtech Foundation, Basque Research and Technology Alliance (BRTA), Donostia/San Sebasti\u00e1n, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210092551"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045548213"],"corresponding_institution_ids":["https://openalex.org/I169108374","https://openalex.org/I4210092551"],"apc_list":null,"apc_paid":null,"fwci":1.1098,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80787039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"56","issue":"3","first_page":"943","last_page":"971"},"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":0.9991000294685364,"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":0.9825999736785889,"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":0.8563559651374817},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8402053713798523},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7819018363952637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6265116333961487},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6154535412788391},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.612260103225708},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5788009166717529},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5593450665473938},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.54188472032547},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5271672606468201},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4500286877155304},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35637253522872925}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8563559651374817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402053713798523},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7819018363952637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6265116333961487},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6154535412788391},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.612260103225708},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5788009166717529},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5593450665473938},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.54188472032547},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5271672606468201},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4500286877155304},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35637253522872925},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10579-021-09572-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-021-09572-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-021-09572-2.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"}],"best_oa_location":{"id":"doi:10.1007/s10579-021-09572-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-021-09572-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-021-09572-2.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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321705","display_name":"Eusko Jaurlaritza","ror":"https://ror.org/00pz2fp31"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4210636016.pdf","grobid_xml":"https://content.openalex.org/works/W4210636016.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W67077090","https://openalex.org/W141732386","https://openalex.org/W177567554","https://openalex.org/W222053410","https://openalex.org/W614252839","https://openalex.org/W1508577659","https://openalex.org/W1914743126","https://openalex.org/W1973152633","https://openalex.org/W2047295649","https://openalex.org/W2061118075","https://openalex.org/W2065565011","https://openalex.org/W2101096097","https://openalex.org/W2101105183","https://openalex.org/W2104103102","https://openalex.org/W2105673178","https://openalex.org/W2107695330","https://openalex.org/W2124807415","https://openalex.org/W2133564696","https://openalex.org/W2139812240","https://openalex.org/W2141068210","https://openalex.org/W2145080939","https://openalex.org/W2148708890","https://openalex.org/W2159872955","https://openalex.org/W2250288378","https://openalex.org/W2251013614","https://openalex.org/W2467834614","https://openalex.org/W2508809683","https://openalex.org/W2509928212","https://openalex.org/W2511852057","https://openalex.org/W2512924740","https://openalex.org/W2513102468","https://openalex.org/W2513660799","https://openalex.org/W2513768144","https://openalex.org/W2576742006","https://openalex.org/W2579327808","https://openalex.org/W2739740656","https://openalex.org/W2741788241","https://openalex.org/W2742155240","https://openalex.org/W2757920198","https://openalex.org/W2760656271","https://openalex.org/W2765961751","https://openalex.org/W2767899794","https://openalex.org/W2786828416","https://openalex.org/W2797913374","https://openalex.org/W2798389157","https://openalex.org/W2805411799","https://openalex.org/W2889326796","https://openalex.org/W2890007195","https://openalex.org/W2941700260","https://openalex.org/W2960374072","https://openalex.org/W2962735107","https://openalex.org/W2962784628","https://openalex.org/W2963122608","https://openalex.org/W2963216553","https://openalex.org/W2963532001","https://openalex.org/W2963919854","https://openalex.org/W2964048171","https://openalex.org/W2964343359","https://openalex.org/W2970015022","https://openalex.org/W2997181101","https://openalex.org/W3031596474","https://openalex.org/W4206027098","https://openalex.org/W6606385677","https://openalex.org/W6608156005","https://openalex.org/W6619288620","https://openalex.org/W6629088714","https://openalex.org/W6739901393","https://openalex.org/W6752458592","https://openalex.org/W6931689928","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2382566571","https://openalex.org/W2357409937","https://openalex.org/W2354515814","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W2990352702"],"abstract_inverted_index":{"Abstract":[0],"Comparable":[1],"corpora":[2],"can":[3,214],"benefit":[4],"the":[5,24,38,47,54,89,105,109,121,125,137,158,171,176],"development":[6],"of":[7,26,49,85,88,92,113,127,142,185],"Neural":[8,200],"Machine":[9,201],"Translation":[10],"models,":[11,122],"in":[12,57,67,136,148,178],"particular":[13],"for":[14,31,63,74,199,219],"under-resourced":[15],"languages.":[16],"We":[17],"present":[18],"a":[19,27,82,220],"case":[20],"study":[21],"centred":[22],"on":[23],"exploitation":[25],"large":[28],"comparable":[29,132,173],"corpus":[30],"Basque-Spanish,":[32],"created":[33],"from":[34],"independently-produced":[35],"news":[36],"by":[37,104],"Basque":[39],"public":[40],"broadcaster":[41],"eitb":[42],",":[43],"where":[44],"we":[45],"evaluate":[46],"impact":[48],"different":[50],"techniques":[51],"to":[52,59,119,129,168,188,193,216],"exploit":[53,170],"original":[55],"data,":[56],"order":[58],"complement":[60],"parallel":[61,75,100,134],"datasets":[62,156],"this":[64,149,179,183],"language":[65],"pair":[66],"both":[68],"translation":[69,222],"directions.":[70],"Two":[71],"efficient":[72],"methods":[73],"sentence":[76],"mining":[77],"are":[78],"explored,":[79],"which":[80],"identified":[81],"common":[83],"core":[84],"approximately":[86],"half":[87],"total":[90],"number":[91],"aligned":[93],"sentences,":[94],"each":[95],"one":[96],"uniquely":[97],"identifying":[98],"valid":[99],"sentences":[101],"not":[102],"captured":[103],"other":[106],"method.":[107],"Filtering":[108],"data":[110,135,144,186,198,213],"via":[111],"identification":[112],"length-difference":[114],"outliers":[115],"proved":[116],"highly":[117],"effective":[118],"improve":[120],"as":[123,196,206],"was":[124],"use":[126,141,195],"tags":[128],"discriminate":[130],"between":[131,209],"and":[133,211],"training":[138,197],"corpora.":[139],"The":[140],"backtranslated":[143],"is":[145],"also":[146,165],"evaluated":[147],"work,":[150],"with":[151],"results":[152,177,218],"indicating":[153],"that":[154,182],"alignment-based":[155],"remain":[157],"most":[159],"beneficial,":[160],"although":[161],"complementary":[162],"backtranslations":[163],"should":[164],"be":[166,189],"included":[167],"fully":[169],"available":[172],"data.":[174],"Overall,":[175],"work":[180],"demonstrate":[181],"type":[184],"needs":[187],"carefully":[190],"analysed":[191],"prior":[192],"its":[194],"Translation,":[202],"since":[203],"issues":[204],"such":[205],"information":[207],"imbalance":[208],"source":[210],"target":[212],"lead":[215],"unoptimal":[217],"given":[221],"pair.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}