{"id":"https://openalex.org/W4412962467","doi":"https://doi.org/10.1007/s10115-025-02520-4","title":"Linguistic entity masking to improve cross-lingual representation of multilingual language models for low-resource languages","display_name":"Linguistic entity masking to improve cross-lingual representation of multilingual language models for low-resource languages","publication_year":2025,"publication_date":"2025-07-19","ids":{"openalex":"https://openalex.org/W4412962467","doi":"https://doi.org/10.1007/s10115-025-02520-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10115-025-02520-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-025-02520-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-025-02520-4.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"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":"Knowledge and Information Systems","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/s10115-025-02520-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078381087","display_name":"Aloka Fernando","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":true,"raw_author_name":"Aloka Fernando","raw_affiliation_strings":["Department of Computer Science & Engineering, University of Moratuwa, Moratuwa, 10400, Sri Lanka"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of Moratuwa, Moratuwa, 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002889503","display_name":"Surangika Ranathunga","orcid":null},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Surangika Ranathunga","raw_affiliation_strings":["School of Mathematical and Computational Sciences, Massey University, Palmerston North, 4443, New Zealand"],"affiliations":[{"raw_affiliation_string":"School of Mathematical and Computational Sciences, Massey University, Palmerston North, 4443, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078381087"],"corresponding_institution_ids":["https://openalex.org/I195740183"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1020162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"67","issue":"11","first_page":"9905","last_page":"9946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.794921875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6981186270713806},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5968441963195801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5451164245605469},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5123125314712524},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4988064765930176},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.47836655378341675},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4775170385837555},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45717954635620117},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4405268430709839}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794921875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6981186270713806},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5968441963195801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5451164245605469},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5123125314712524},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4988064765930176},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.47836655378341675},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4775170385837555},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45717954635620117},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4405268430709839},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10115-025-02520-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-025-02520-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-025-02520-4.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"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":"Knowledge and Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10115-025-02520-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-025-02520-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10115-025-02520-4.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"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":"Knowledge and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320816","display_name":"Massey University","ror":"https://ror.org/052czxv31"},{"id":"https://openalex.org/F4320325939","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412962467.pdf","grobid_xml":"https://content.openalex.org/works/W4412962467.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2250342921","https://openalex.org/W2606964149","https://openalex.org/W2608377846","https://openalex.org/W2758950307","https://openalex.org/W2887476518","https://openalex.org/W2923014074","https://openalex.org/W2933138175","https://openalex.org/W2962735107","https://openalex.org/W2963532001","https://openalex.org/W2963748441","https://openalex.org/W2973088264","https://openalex.org/W3011411500","https://openalex.org/W3035016936","https://openalex.org/W3035032094","https://openalex.org/W3035390927","https://openalex.org/W3038033387","https://openalex.org/W3039695075","https://openalex.org/W3105425516","https://openalex.org/W3137010024","https://openalex.org/W3169369929","https://openalex.org/W3169425228","https://openalex.org/W3175301726","https://openalex.org/W4283766873","https://openalex.org/W4287888493","https://openalex.org/W4306655068","https://openalex.org/W4375869319","https://openalex.org/W4385569995","https://openalex.org/W4385570517","https://openalex.org/W4386566638","https://openalex.org/W4402371530","https://openalex.org/W4402671974","https://openalex.org/W4402683416","https://openalex.org/W4404784034","https://openalex.org/W4410943893","https://openalex.org/W4411630268","https://openalex.org/W6600547436","https://openalex.org/W6611215823"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2949968076","https://openalex.org/W2935811960","https://openalex.org/W2969407538"],"abstract_inverted_index":{"Abstract":[0],"Multilingual":[1],"Pre-trained":[2],"Language":[3,10,73],"models":[4,30],"(multiPLMs),":[5],"trained":[6],"on":[7],"the":[8,26,40,77,96,101,105,124,131,147,173,192],"Masked":[9],"Modelling":[11,74],"(MLM)":[12],"objective":[13],"are":[14,187],"commonly":[15],"being":[16],"used":[17,122],"for":[18,34,236],"cross-lingual":[19,78,132],"tasks":[20],"such":[21],"as":[22,57],"bitext":[23,201],"mining.":[24],"However,":[25,82],"performance":[27],"of":[28,43,80,100,104,134,194],"these":[29],"is":[31,48,55],"still":[32],"suboptimal":[33],"low-resource":[35,212],"languages":[36],"(LRLs).":[37],"To":[38],"improve":[39,130],"language":[41,213],"representation":[42,79],"a":[44,112,158,162,169,225,230],"given":[45],"multiPLM,":[46],"it":[47],"possible":[49],"to":[50,92,120,128,139,146,168],"further":[51,129],"pre-train":[52],"it.":[53],"This":[54],"known":[56],"continual":[58,65,125],"pre-training.":[59],"Previous":[60],"research":[61],"has":[62],"shown":[63],"that":[64,222],"pre-training":[66,126,224],"with":[67,71,227,234],"MLM":[68,86,140,183],"and":[69,87,141,153,184,206,217],"subsequently":[70],"Translation":[72],"(TLM)":[75],"improves":[76],"multiPLMs.":[81,136],"during":[83],"masking,":[84],"both":[85],"TLM":[88],"give":[89],"equal":[90],"weight":[91],"all":[93,237],"tokens":[94,186],"in":[95,123,161,182],"input":[97],"sequence,":[98],"irrespective":[99],"linguistic":[102,148,174],"properties":[103],"tokens.":[106],"In":[107,137],"this":[108],"paper,":[109],"we":[110,165],"introduce":[111],"novel":[113],"masking":[114,145,167],"strategy,":[115],"Linguistic":[116],"Entity":[117],"Masking":[118],"(LEM)":[119],"be":[121],"step":[127],"representations":[133],"existing":[135],"contrast":[138],"TLM,":[142,185],"LEM":[143,195,228],"limits":[144],"entity":[149,175],"types":[150],"nouns,":[151],"verbs":[152],"named":[154],"entities,":[155],"which":[156],"hold":[157],"higher":[159],"prominence":[160],"sentence.":[163],"Secondly,":[164],"limit":[166],"single":[170],"token":[171],"within":[172],"span":[176],"thus":[177],"keeping":[178],"more":[179],"context,":[180],"whereas,":[181],"masked":[188],"randomly.":[189],"We":[190],"evaluate":[191],"effectiveness":[193],"using":[196,210],"three":[197,211,238],"downstream":[198],"tasks,":[199],"namely":[200],"mining,":[202],"parallel":[203],"data":[204],"curation":[205],"code-mixed":[207],"sentiment":[208],"analysis":[209],"pairs":[214],"English-Sinhala,":[215],"English-Tamil,":[216],"Sinhala-Tamil.":[218],"Experiment":[219],"results":[220],"show":[221],"continually":[223,232],"multiPLM":[226,231],"outperforms":[229],"pre-trained":[233],"MLM+TLM":[235],"tasks.":[239]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
