Hyperparameter Optimization on Neural Machine Translation

dc.contributor.author Agnihotri, Souparni
dc.contributor.department Electrical and Computer Engineering
dc.contributor.majorProfessor Chinmay Hegde
dc.date 2019-09-20T20:29:43.000
dc.date.accessioned 2020-06-30T01:32:31Z
dc.date.available 2020-06-30T01:32:31Z
dc.date.copyright Tue Jan 01 00:00:00 UTC 2019
dc.date.issued 2019-01-01
dc.description.abstract <p>With the growth of deep learning in the recent years, there have been several models created to tackle different real world goals, autonomously. One such goal is the automatic translation of text from one language to another. This is commonly known as Neural Machine Translation (NMT). NMT has proved to be a significant challenge to achieve, given the fluidity of human language. Most NMT models rely on Recurrent Neural Networks (RNNs) and deep Long Short-Term Memory networks (LSTMs). In this study, we will explore the Sequence to Sequence Learning with Neural Networks Model (Sutskever et al. (5)) and perform an ablation study of the model on two different data sets - the English-Vietnamese parallel corpus by the IWSLT Evaluation Campaign, and the German-English parallel corpus obtained from the WMT Evaluation Campaign.</p>
dc.format.mimetype application/pdf
dc.identifier archive/lib.dr.iastate.edu/creativecomponents/124/
dc.identifier.articleid 1228
dc.identifier.contextkey 14317168
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath creativecomponents/124
dc.identifier.uri https://dr.lib.iastate.edu/handle/20.500.12876/16651
dc.source.bitstream archive/lib.dr.iastate.edu/creativecomponents/124/Hyperparameter_Optimisation_for_NMT.pdf|||Fri Jan 14 19:20:54 UTC 2022
dc.subject.disciplines Artificial Intelligence and Robotics
dc.subject.keywords Neural Machine Translation
dc.subject.keywords Hyperparameter Optimization
dc.subject.keywords Machine Learning
dc.subject.keywords Neural Networks
dc.title Hyperparameter Optimization on Neural Machine Translation
dc.type article
dc.type.genre creativecomponent
dspace.entity.type Publication
relation.isOrgUnitOfPublication a75a044c-d11e-44cd-af4f-dab1d83339ff
thesis.degree.discipline Computer Engineering
thesis.degree.level creativecomponent
Original bundle
Now showing 1 - 1 of 1
789.01 KB
Adobe Portable Document Format