Danish Asylum Adjudication using Deep Neural Networks and Natural Language Processing
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Danish Asylum Adjudication using Deep Neural Networks and Natural Language Processing. / Muddamsetty, Satya Mahesh; Jahromi, Mohammad Naser Sabet; Moeslund, Thomas B.; Gammeltoft-Hansen, Thomas.
Danish Asylum Adjudication using Deep Neural Networks and Natural Language Processing. Springer, 2023. p. 1-13.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Danish Asylum Adjudication using Deep Neural Networks and Natural Language Processing
AU - Muddamsetty, Satya Mahesh
AU - Jahromi, Mohammad Naser Sabet
AU - Moeslund, Thomas B.
AU - Gammeltoft-Hansen, Thomas
PY - 2023
Y1 - 2023
N2 - TheDanishasylumadjudicationprocedure isatwo-tiered system,withtheImmigrationServicemakinginitialdeterminationsand theDanishRefugeeAppealsBoard(RAB)automaticallyappealingcases thatarerejected.Thisstudyaimstoemployadeepneuralnetwork(DNN)basedNaturalLanguageProcessing(NLP)pipeline topredictasylum decision-makingoutcomesusingadataset of over 15,515DanishasylumdecisionsprovidedbytheDanishRefugeeAppealsBoard(RAB) betweenJanuary1995andJanuary2021.Thisresearchseekstoimprove theperformanceandeffectivenessofdecision-makinginasylumcasesby addressingkeychallenges,suchasmodelingtheasylumdecision-making problemusingNLP-basedDNNsanddealingwithclassimbalanceissues. OurpreliminaryresultsindicatethatDNN-basedNLPpredictivemodels arecapableof learningmeaningful representationsofasylumcaseswith highprecisionandrecall,particularlywhenclassweightsareconsidered thanthebaselineDNNmodel.
AB - TheDanishasylumadjudicationprocedure isatwo-tiered system,withtheImmigrationServicemakinginitialdeterminationsand theDanishRefugeeAppealsBoard(RAB)automaticallyappealingcases thatarerejected.Thisstudyaimstoemployadeepneuralnetwork(DNN)basedNaturalLanguageProcessing(NLP)pipeline topredictasylum decision-makingoutcomesusingadataset of over 15,515DanishasylumdecisionsprovidedbytheDanishRefugeeAppealsBoard(RAB) betweenJanuary1995andJanuary2021.Thisresearchseekstoimprove theperformanceandeffectivenessofdecision-makinginasylumcasesby addressingkeychallenges,suchasmodelingtheasylumdecision-making problemusingNLP-basedDNNsanddealingwithclassimbalanceissues. OurpreliminaryresultsindicatethatDNN-basedNLPpredictivemodels arecapableof learningmeaningful representationsofasylumcaseswith highprecisionandrecall,particularlywhenclassweightsareconsidered thanthebaselineDNNmodel.
M3 - Article in proceedings
SP - 1
EP - 13
BT - Danish Asylum Adjudication using Deep Neural Networks and Natural Language Processing
PB - Springer
ER -
ID: 377826428