{"id":"https://openalex.org/W7204522071","doi":"https://doi.org/10.13140/rg.2.2.28180.87688","title":"EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation","display_name":"EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204522071","doi":"https://doi.org/10.13140/rg.2.2.28180.87688"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.29511","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29511","pdf_url":"https://arxiv.org/pdf/2609.29511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.29511","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002889503","display_name":"Surangika Ranathunga","orcid":"https://orcid.org/0000-0003-0701-0204","observed_orcids":["https://orcid.org/0000-0003-0701-0204"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Surangika Ranathunga","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148480256","display_name":"Nisansa De Silva","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nisansa De Silva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078381087","display_name":"Aloka Fernando","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aloka Fernando","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120625702","display_name":"Kavindu Warnakulasuriya","orcid":"https://orcid.org/0009-0002-2462-147X","observed_orcids":["https://orcid.org/0009-0002-2462-147X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kavindu Warnakulasuriya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038627637","display_name":"Isuru Wijesiri","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Isuru Wijesiri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004264684","display_name":"Menan Velayuthan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Menan Velayuthan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148498710","display_name":"Charitha Rathnayaka","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charitha Rathnayaka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148563723","display_name":"Thivaharan Varatharajan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thivaharan Varatharajan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148508196","display_name":"Sajeevi Silva","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sajeevi Silva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049897798","display_name":"Piumi Kavindya Kandanaarachchi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piumi Kandanaarachchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049911731","display_name":"Uthayasanker Thayasivam","orcid":"https://orcid.org/0000-0002-3936-8174","observed_orcids":["https://orcid.org/0000-0002-3936-8174"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Uthayasanker Thayasivam","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":0.9932000041007996,"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":0.9932000041007996,"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":0.003700000001117587,"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/T10759","display_name":"Translation Studies and Practices","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.6629999876022339},{"id":"https://openalex.org/keywords/multi-domain-translation","display_name":"multi-domain translation","score":0.7239999771118164},{"id":"https://openalex.org/keywords/translation-benchmark","display_name":"translation benchmark","score":0.8080000281333923},{"id":"https://openalex.org/keywords/english-spanish-translation","display_name":"English-Spanish translation","score":0.6549999713897705},{"id":"https://openalex.org/keywords/spanish-italian-translation","display_name":"Spanish-Italian translation","score":0.5389999747276306},{"id":"https://openalex.org/keywords/english-italian-translation","display_name":"English-Italian translation","score":0.5839999914169312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912000179290771},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.607200026512146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.574400007724762},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5024999976158142},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.450300008058548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2574000060558319}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2609.29511","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29511","pdf_url":"https://arxiv.org/pdf/2609.29511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2609.29511","doi":"https://doi.org/10.48550/arxiv.2609.29511","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.29511","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.13140/rg.2.2.28180.87688","doi":"https://doi.org/10.13140/rg.2.2.28180.87688","is_oa":false,"landing_page_url":"https://doi.org/10.13140/rg.2.2.28180.87688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.29511","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29511","pdf_url":"https://arxiv.org/pdf/2609.29511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325939","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204522071.pdf","grobid_xml":"https://content.openalex.org/works/W7204522071.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4405903293","https://openalex.org/W4281703421","https://openalex.org/W3151076294","https://openalex.org/W2807684985","https://openalex.org/W3137881600","https://openalex.org/W7171563038","https://openalex.org/W4404782168","https://openalex.org/W7171959523","https://openalex.org/W4404780990","https://openalex.org/W3029357778"],"abstract_inverted_index":{"Machine":[0],"Translation":[1],"(MT)":[2],"for":[3,39,50,58,86,141],"low-resource":[4,142],"languages":[5],"remains":[6],"far":[7],"behind":[8],"that":[9],"of":[10,83,124],"high-resource":[11],"languages,":[12],"and":[13,37,42,60,100,107,114,118,138,146],"the":[14,122,129],"gap":[15],"is":[16,24,128],"widest":[17],"in":[18],"specialised":[19],"domains,":[20,52],"where":[21],"parallel":[22,35,135],"data":[23,49,136,145],"scarce":[25],"or":[26],"entirely":[27],"absent.":[28],"We":[29],"present":[30],"EnSiTa,":[31],"a":[32,70,92,95],"trilingual":[33],"multi-domain":[34,119,134],"dataset":[36],"benchmark":[38],"English,":[40],"Sinhala":[41],"Tamil.":[43],"EnSiTa":[44],"provides":[45],"human":[46],"post-edited":[47],"training":[48],"seven":[51],"plus":[53],"manually":[54],"translated":[55],"test":[56],"sets":[57],"those":[59],"one":[61],"additional":[62],"domain,":[63],"all":[64,87],"produced":[65],"by":[66],"professional":[67],"translators":[68],"under":[69],"multi-year,":[71],"rigorously":[72],"quality-controlled":[73],"process.":[74],"Using":[75],"this":[76,127],"dataset,":[77],"we":[78],"conduct":[79],"an":[80],"extensive":[81,131],"study":[82],"domain-specific":[84],"MT":[85],"six":[88],"language":[89],"directions,":[90],"fine-tuning":[91],"from-scratch":[93],"Transformer,":[94],"pre-trained":[96],"translation":[97],"model":[98,112],"(NLLB-600M),":[99],"decoder-only":[101],"LLMs":[102],"(Gemma":[103],"3":[104],"family,":[105],"1B-12B,":[106],"TranslateGemma)":[108],"across":[109],"training-data":[110],"sizes,":[111],"scales,":[113],"in-domain,":[115],"cross-domain,":[116],"multilingual":[117],"settings.":[120],"To":[121],"best":[123],"our":[125],"knowledge,":[126],"most":[130],"systematically":[132],"documented":[133],"creation":[137],"benchmarking":[139],"effort":[140],"MT.":[143],"Our":[144],"models":[147],"will":[148],"be":[149],"publicly":[150],"released.":[151]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-08-29T00:00:00"}