{"id":"https://openalex.org/W4384816577","doi":"https://doi.org/10.48550/arxiv.2307.08714","title":"Cross-Lingual NER for Financial Transaction Data in Low-Resource Languages","display_name":"Cross-Lingual NER for Financial Transaction Data in Low-Resource Languages","publication_year":2023,"publication_date":"2023-07-16","ids":{"openalex":"https://openalex.org/W4384816577","doi":"https://doi.org/10.48550/arxiv.2307.08714"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2307.08714","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.08714","pdf_url":"https://arxiv.org/pdf/2307.08714","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.08714","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104145215","display_name":"Sunisth Kumar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Sunisth","raw_affiliation_strings":["Gurugram , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gurugram , India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032530451","display_name":"Davide Liu","orcid":"https://orcid.org/0000-0003-0380-404X","observed_orcids":["https://orcid.org/0000-0003-0380-404X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Davide","raw_affiliation_strings":["Genify Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genify Beijing , China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010092490","display_name":"Alexandre Boulenger","orcid":"https://orcid.org/0000-0001-8120-0001","observed_orcids":["https://orcid.org/0000-0001-8120-0001"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boulenger, Alexandre","raw_affiliation_strings":["Genify Abu Dhabi , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genify Abu Dhabi , UAE","institution_ids":[]}]}],"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":3,"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/T10028","display_name":"Topic Modeling","score":0.9951000213623047,"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":0.9951000213623047,"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":0.00139999995008111,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/cross-lingual-named-entity-recognition","display_name":"cross-lingual named entity recognition","score":0.9990000128746033},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8899999856948853},{"id":"https://openalex.org/keywords/financial-transaction-data","display_name":"financial transaction data","score":0.9020000100135803},{"id":"https://openalex.org/keywords/semi-structured-text","display_name":"semi-structured text","score":0.8870000243186951},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.8410000205039978},{"id":"https://openalex.org/keywords/consistency-regularization","display_name":"consistency regularization","score":0.9890000224113464},{"id":"https://openalex.org/keywords/xlm-r","display_name":"XLM-R","score":0.8610000014305115},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.43299999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7873871326446533},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6695306897163391},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6331267952919006},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6175752282142639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.588333010673523},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5234262943267822},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.4960053861141205},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4209345579147339},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.41398143768310547},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22442805767059326},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21262454986572266},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2307.08714","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.08714","pdf_url":"https://arxiv.org/pdf/2307.08714","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2307.08714","doi":"https://doi.org/10.48550/arxiv.2307.08714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.08714","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.08714","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.08714","pdf_url":"https://arxiv.org/pdf/2307.08714","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384816577.pdf","grobid_xml":"https://content.openalex.org/works/W4384816577.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2983040767","https://openalex.org/W3213849509"],"related_works":["https://openalex.org/W4310609185","https://openalex.org/W2757931423","https://openalex.org/W7167927534","https://openalex.org/W2808481912","https://openalex.org/W7167816407","https://openalex.org/W7167413217","https://openalex.org/W7169718962","https://openalex.org/W7165202566","https://openalex.org/W7167833596","https://openalex.org/W7171313985"],"abstract_inverted_index":{"We":[0,63,115],"propose":[1],"an":[2],"efficient":[3],"modeling":[4,26,119],"framework":[5,27,186],"for":[6,189],"cross-lingual":[7],"named":[8],"entity":[9],"recognition":[10,104],"in":[11,70,147,163,169,173,194],"semi-structured":[12,76,182],"text":[13],"data.":[14,183],"Our":[15,151],"approach":[16],"relies":[17],"on":[18,37,58,82,134,144,200],"both":[19,201],"knowledge":[20,29,87],"distillation":[21],"and":[22,72,80,108,203],"consistency":[23,52],"training.":[24],"The":[25,47,184],"leverages":[28],"from":[30,88,111],"a":[31,42,139,170,177],"large":[32],"language":[33,137,172],"model":[34,49,100,141],"(XLMRoBERTa)":[35],"pre-trained":[36,133],"the":[38,59,84,103,135,148,174],"source":[39],"language,":[40],"with":[41,211],"student-teacher":[43],"relationship":[44],"(knowledge":[45],"distillation).":[46],"student":[48],"incorporates":[50],"unsupervised":[51],"training":[53],"(with":[54],"KL":[55],"divergence":[56],"loss)":[57],"low-resource":[60,171,207],"target":[61,136,149],"language.":[62,150],"employ":[64],"two":[65],"independent":[66],"datasets":[67],"of":[68,86,105,176,181],"SMSs":[69],"English":[71,89,112,164,202,212],"Arabic,":[73],"each":[74],"carrying":[75],"banking":[77],"transaction":[78],"information,":[79],"focus":[81],"exhibiting":[83],"transfer":[85],"to":[90,94,113,128,158,160,165],"Arabic.":[91,114],"With":[92],"access":[93],"only":[95],"30":[96],"labeled":[97,145,179],"samples,":[98],"our":[99,118],"can":[101],"generalize":[102],"merchants,":[106],"amounts,":[107],"other":[109],"fields":[110],"show":[116,153],"that":[117,154],"approach,":[120],"while":[121],"efficient,":[122],"performs":[123],"best":[124],"overall":[125],"when":[126],"compared":[127],"state-of-the-art":[129],"approaches":[130],"like":[131],"DistilBERT":[132],"or":[138,205,213],"supervised":[140],"directly":[142],"trained":[143],"data":[146],"experiments":[152],"it":[155],"is":[156],"enough":[157],"learn":[159],"recognize":[161],"entities":[162],"reach":[166],"reasonable":[167],"performance":[168],"presence":[175],"few":[178],"samples":[180],"proposed":[185],"has":[187],"implications":[188],"developing":[190],"multi-lingual":[191],"applications,":[192],"especially":[193],"geographies":[195],"where":[196],"digital":[197],"endeavors":[198],"rely":[199],"one":[204],"more":[206],"language(s),":[208],"sometimes":[209],"mixed":[210],"employed":[214],"singly.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-07-21T00:00:00"}