{"id":"https://openalex.org/W7113268979","doi":null,"title":"LLMs for Machine Translation in Medium-Resourced Languages: From Transfer Abilities to the Impacts of Parallel Data","display_name":"LLMs for Machine Translation in Medium-Resourced Languages: From Transfer Abilities to the Impacts of Parallel Data","publication_year":2024,"publication_date":"2024-06-05","ids":{"openalex":"https://openalex.org/W7113268979"},"language":"en","primary_location":{"id":"pmh:oai:upcommons.upc.edu:2117/422439","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/422439","pdf_url":"https://upcommons.upc.edu/bitstreams/3b1590d9-0cc0-4815-9fd7-05eb97b07646/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/masterThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://upcommons.upc.edu/bitstreams/3b1590d9-0cc0-4815-9fd7-05eb97b07646/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Prats Cristi\u00e0, Jaume","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Prats Cristi\u00e0, Jaume","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9639000296592712,"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":0.9639000296592712,"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":0.031099999323487282,"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":0.0010999999940395355,"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/large-language-models","display_name":"large language models","score":0.8220000267028809},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.9890000224113464},{"id":"https://openalex.org/keywords/iberian-language","display_name":"Iberian language","score":0.8640000224113464},{"id":"https://openalex.org/keywords/catalan","display_name":"Catalan","score":0.9580000042915344},{"id":"https://openalex.org/keywords/spanish-language","display_name":"Spanish language","score":1.0},{"id":"https://openalex.org/keywords/decoder-only-models","display_name":"decoder-only models","score":0.8579999804496765},{"id":"https://openalex.org/keywords/fine-tuning-strategies","display_name":"fine-tuning strategies","score":0.8090000152587891},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.9380000233650208},{"id":"https://openalex.org/keywords/cross-lingual-transfer","display_name":"cross-lingual transfer","score":0.9710000157356262},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"natural language understanding","score":0.8669999837875366},{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.6019999980926514}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7605000138282776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168999910354614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5899999737739563},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5773000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.570900022983551},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3528999984264374},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3059999942779541},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:upcommons.upc.edu:2117/422439","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/422439","pdf_url":"https://upcommons.upc.edu/bitstreams/3b1590d9-0cc0-4815-9fd7-05eb97b07646/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/masterThesis"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/422439","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/422439","pdf_url":"https://upcommons.upc.edu/bitstreams/3b1590d9-0cc0-4815-9fd7-05eb97b07646/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/masterThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7113268979.pdf","grobid_xml":"https://content.openalex.org/works/W7113268979.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2468328197","https://openalex.org/W2563351168","https://openalex.org/W2626778328","https://openalex.org/W2938704169","https://openalex.org/W2963096510","https://openalex.org/W2981852735","https://openalex.org/W2988394319","https://openalex.org/W3030163527","https://openalex.org/W3168867926","https://openalex.org/W4226265366","https://openalex.org/W4229005866","https://openalex.org/W4285077564","https://openalex.org/W4317547647","https://openalex.org/W4321472057","https://openalex.org/W4322718191","https://openalex.org/W4379468930","https://openalex.org/W4385571264","https://openalex.org/W4385572075","https://openalex.org/W4385572225","https://openalex.org/W4385750324","https://openalex.org/W4386977391","https://openalex.org/W4388444775","https://openalex.org/W4389157038","https://openalex.org/W4389518906","https://openalex.org/W4389519545","https://openalex.org/W4389524077","https://openalex.org/W4390307319","https://openalex.org/W4392271855","https://openalex.org/W4395680645","https://openalex.org/W4401042993","https://openalex.org/W4402671974","https://openalex.org/W4404780950","https://openalex.org/W4404781335","https://openalex.org/W4404783397","https://openalex.org/W7133227460","https://openalex.org/W7133233472"],"related_works":["https://openalex.org/W4399695657","https://openalex.org/W4386977391","https://openalex.org/W4407186828","https://openalex.org/W6979238655","https://openalex.org/W4404781482","https://openalex.org/W4401042989","https://openalex.org/W4406911809","https://openalex.org/W4402670267","https://openalex.org/W4403589969","https://openalex.org/W4405253710"],"abstract_inverted_index":{"This":[0],"thesis":[1,133],"delves":[2],"into":[3,117],"the":[4,13,52,66,78,90,100,109,113,118,132,146],"capabilities":[5],"of":[6,15,54,69,80,83,92,104,112,148],"decoder-only":[7,70],"Large":[8],"Language":[9],"Models":[10],"(LLMs)":[11],"in":[12,108,136],"domain":[14],"machine":[16],"translation":[17,87,143],"(MT),":[18],"with":[19],"a":[20],"focus":[21],"on":[22,57,86,99],"Iberian":[23],"languages,":[24],"particularly":[25],"Catalan":[26],"and":[27,34,51,123],"Spanish.":[28],"Through":[29],"extensive":[30],"experimentation":[31],"using":[32],"Falcon-7B":[33],"Aguila-":[35],"7B":[36],"models,":[37],"various":[38],"aspects":[39],"are":[40,126],"investigated,":[41],"including":[42],"fine-tuning":[43,56,93],"strategies,":[44],"parameter-":[45],"efficient":[46],"techniques,":[47],"cross-lingual":[48,101],"transfer":[49,102,119],"abilities,":[50],"impact":[53,79],"MT":[55,73,122],"natural":[58],"language":[59],"understanding":[60],"(NLU)":[61],"tasks.":[62,74],"Key":[63],"findings":[64],"reveal":[65],"promising":[67],"potential":[68],"models":[71,107],"for":[72,151],"The":[75],"study":[76],"clarifies":[77],"different":[81],"quantities":[82],"parallel":[84],"data":[85],"performance,":[88],"emphasizing":[89],"significance":[91],"strategies.":[94],"Additionally,":[95],"it":[96],"sheds":[97],"light":[98],"abilities":[103,120],"decoder-":[105],"only":[106],"related":[110],"languages":[111],"study.":[114],"Moreover,":[115],"insights":[116],"between":[121],"NLU":[124],"tasks":[125],"provided,":[127],"highlighting":[128],"associated":[129],"constraints.":[130],"Furthermore,":[131],"identifies":[134],"shortcomings":[135],"COMET":[137],"metrics":[138,150],"when":[139],"handling":[140],"off-":[141],"target":[142],"errors,":[144],"higlighting":[145],"use":[147],"multiple":[149],"result":[152],"interpretation.":[153]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-12-10T00:00:00"}
