{"id":"https://openalex.org/W7167898369","doi":"https://doi.org/10.1109/access.2026.3712041","title":"Using English-Based NLP Tools for Domain-Specific Text in Foreign Languages","display_name":"Using English-Based NLP Tools for Domain-Specific Text in Foreign Languages","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7167898369","doi":"https://doi.org/10.1109/access.2026.3712041"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3712041","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3712041","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3712041","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107185211","display_name":"Naif Alatrush","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naif Alatrush","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":"https://orcid.org/0009-0005-7903-6544","affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036796573","display_name":"Luay Abdeljaber","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luay Abdeljaber","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":"https://orcid.org/0009-0000-0933-7425","affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069844991","display_name":"Javier Osorio","orcid":"https://orcid.org/0000-0002-4548-7794"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Javier Osorio","raw_affiliation_strings":["University of Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115568002","display_name":"Dagmar Heintze","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dagmar Heintze","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":"https://orcid.org/0009-0008-3547-8254","affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140399315","display_name":"Brikena Liko","orcid":null},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brikena Liko","raw_affiliation_strings":["University of Arizona"],"raw_orcid":"https://orcid.org/0000-0003-0384-7779","affiliations":[{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128332083","display_name":"Patrick T. Brandt","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick T. Brandt","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005002693","display_name":"Latifur Khan","orcid":"https://orcid.org/0000-0002-9300-1576"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Latifur Khan","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":"https://orcid.org/0000-0002-9300-1576","affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140414940","display_name":"Vito J. D\u2019Orazio","orcid":null},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vito J. D'Orazio","raw_affiliation_strings":["West Virginia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"West Virginia University","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079025806","display_name":"Sultan Alsarra","orcid":null},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Sultan Alsarra","raw_affiliation_strings":["King Saud University"],"raw_orcid":"https://orcid.org/0009-0000-3908-756X","affiliations":[{"raw_affiliation_string":"King Saud University","institution_ids":["https://openalex.org/I28022161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86636092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"111122","last_page":"111139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.29179999232292175,"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":0.29179999232292175,"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":0.09040000289678574,"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/T12031","display_name":"Speech and dialogue systems","score":0.06689999997615814,"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/foreign-language","display_name":"Foreign language","score":0.38999998569488525},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.27239999175071716},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2685999870300293},{"id":"https://openalex.org/keywords/word-sense-disambiguation","display_name":"Word-sense disambiguation","score":0.25130000710487366},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.24709999561309814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170999884605408},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7305999994277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6779000163078308},{"id":"https://openalex.org/C114010052","wikidata":"https://www.wikidata.org/wiki/Q150352","display_name":"Foreign language","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.25130000710487366},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.24709999561309814},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.24089999496936798}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3712041","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3712041","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b54c30cb5af34160922a79078b40da07","is_oa":false,"landing_page_url":"https://doaj.org/article/b54c30cb5af34160922a79078b40da07","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 111122-111139 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3712041","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3712041","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7523161172866821}],"awards":[{"id":"https://openalex.org/G3239984274","display_name":"Frameworks: Infrastructure For Political And Social Event Data using Machine Learning","funder_award_id":"2311142","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Social":[0],"scientists":[1],"often":[2,159],"machine-translate":[3],"foreign-language":[4,41],"texts":[5],"into":[6],"English":[7],"and":[8,45,56,67,88,94,158],"apply":[9],"English-based":[10,181],"natural":[11,36,182],"language":[12,37,183],"processing":[13,38,184],"tools":[14,185],"without":[15],"systematically":[16],"evaluating":[17],"translation":[18,54,77,97],"quality":[19,90],"or":[20,161],"annotation":[21,119],"efficiency.":[22],"To":[23],"address":[24],"this":[25,27],"problem,":[26],"study":[28],"provides":[29],"evidence-based":[30],"guidance":[31],"for":[32,59,112,178],"researchers":[33,179],"applying":[34],"English-centric":[35],"to":[39,71,122],"domain-specific":[40,60,188],"corpora.":[42,189],"We":[43,103],"provide":[44,174],"empirically":[46],"validate":[47],"a":[48,117,167,175],"structured":[49],"framework":[50],"combining":[51],"multi-system":[52],"machine":[53,76,96],"evaluation":[55],"active":[57,107],"learning":[58,108],"text":[61],"classification.":[62],"Using":[63],"11,493":[64],"parallel":[65],"Spanish":[66],"Arabic":[68],"sentences":[69],"aligned":[70],"English,":[72],"we":[73],"compare":[74],"four":[75],"systems":[78,98],"(Google":[79],"Translate,":[80],"Deep,":[81],"DeepL,":[82],"OPUS)":[83],"using":[84,110,165,180],"SacreBLEU,":[85],"METEOR,":[86],"COMET,":[87],"BERTScore":[89],"scores.":[91],"Across":[92],"languages":[93],"metrics,":[95],"yield":[99],"statistically":[100],"comparable":[101],"performance.":[102],"then":[104],"evaluate":[105],"eight":[106],"strategies":[109],"ConfliBERT":[111],"political":[113],"conflict":[114],"classification":[115,130],"under":[116],"20%":[118],"budget,":[120],"corresponding":[121],"1,155":[123],"samples":[124],"from":[125],"the":[126,151],"training":[127],"split.":[128],"Binary":[129],"exceeds":[131],"F1":[132],"=":[133],"0.90,":[134],"while":[135],"QuadClass":[136],"multi-class":[137],"performance":[138,153],"peaks":[139],"around":[140],"F<inline-formula>":[141],"<tex-math":[142],"notation=\"LaTeX\">$1~\\approx":[143],"~0.75$":[144],"</tex-math></inline-formula>.":[145],"The":[146],"Ensemble":[147],"Intersection":[148],"strategy":[149],"achieves":[150],"highest":[152],"in":[154],"53%":[155],"of":[156,169],"tasks":[157],"matches":[160],"surpasses":[162],"full-dataset":[163],"results":[164,173],"only":[166],"fraction":[168],"labeled":[170],"data.":[171],"These":[172],"practical":[176],"workflow":[177],"on":[186],"foreign-language,":[187]},"counts_by_year":[],"updated_date":"2026-07-25T05:54:39.514286","created_date":"2026-07-11T00:00:00"}