{"id":"https://openalex.org/W7126452893","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.100","title":"Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity","display_name":"Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126452893","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.100"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.100","pdf_url":"https://aclanthology.org/2024.findings-eacl.100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.100.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093876037","display_name":"Eric Khiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Khiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093876038","display_name":"Hasti Toossi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hasti Toossi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093876039","display_name":"David Anugraha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Anugraha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124676056","display_name":"Jinyu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124560354","display_name":"Jiaxu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124663250","display_name":"Juan de (1470?-1525?). Auteur du texte Flores","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Flores","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093876040","display_name":"Leandro Acros Roman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leandro Roman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124651248","display_name":"A. Seza Do\u011fru\u00f6z","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Seza Do\u011fru\u00f6z","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124653775","display_name":"En-Shiun Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"En-Shiun Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57310385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1474","last_page":"1486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8274999856948853,"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":0.8274999856948853,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.012900000438094139,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.010499999858438969,"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/domain","display_name":"Domain (mathematical analysis)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46369999647140503},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4375999867916107},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4327999949455261},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3474999964237213},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3449000120162964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6500999927520752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635200023651123},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46369999647140503},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4327999949455261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2639999985694885}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.100","pdf_url":"https://aclanthology.org/2024.findings-eacl.100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.100","pdf_url":"https://aclanthology.org/2024.findings-eacl.100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126452893.pdf","grobid_xml":"https://content.openalex.org/works/W7126452893.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"and":[1,10,40,61,64,70],"testing":[2,62],"a":[3],"multilingual":[4],"large":[5],"language":[6,24,66],"model":[7],"is":[8],"expensive":[9],"challenging":[11],"for":[12],"low-resource":[13],"languages":[14],"(LRLs).While":[15],"previous":[16],"studies":[17],"have":[18],"predicted":[19],"the":[20,50,53,56,65,83,92,98],"performance":[21,99],"of":[22,52,100],"natural":[23],"processing":[25],"(NLP)":[26],"tasks":[27],"using":[28],"machine":[29],"learning":[30],"methods,":[31],"they":[32],"primarily":[33],"focus":[34],"on":[35,44,96],"high-resource":[36],"languages,":[37],"overlooking":[38],"LRLs":[39],"shifts":[41],"across":[42],"domains.Focusing":[43],"LRLs,":[45],"we":[46],"investigate":[47],"three":[48],"factors:":[49],"size":[51],"fine-tuning":[54,60],"corpus,":[55],"domain":[57,89],"similarity":[58,67,90],"between":[59,68],"corpora,":[63],"source":[69],"target":[71],"languages.We":[72],"employ":[73],"classical":[74],"regression":[75],"models":[76],"to":[77],"assess":[78],"how":[79],"these":[80],"factors":[81],"impact":[82,95],"model's":[84],"performance.Our":[85],"results":[86],"indicate":[87],"that":[88],"has":[91],"most":[93],"critical":[94],"predicting":[97],"Machine":[101],"Translation":[102],"models.":[103]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}