Show simple item record

dc.contributor.advisorChin, Sangen_US
dc.contributor.authorHarer, Jacob Alexanderen_US
dc.date.accessioned2020-02-27T15:09:11Z
dc.date.available2020-02-27T15:09:11Z
dc.date.issued2019
dc.identifier.urihttps://hdl.handle.net/2144/39550
dc.description.abstractRecent advances in Neural Machine Translation (NMT) systems have achieved impressive results on language translation tasks. However, the success of these systems has been limited when applied to similar low-resource tasks, such as language correction. In these cases, datasets are often small whilst still containing long sequences, leading to significant overfitting and poor generalization. In this thesis we study issues preventing widespread adoption of NMT systems into low resource tasks, with a special focus on sequence correction for both code and language. We propose two novel techniques for handling these low-resource tasks. The first uses Generative Adversarial Networks to handle datasets without paired data. This technique allows the use of available unpaired datasets which are typically much larger than paired datasets since they do not require manual annotation. We first develop a methodology for generation of discrete sequences using a Wasserstein Generative Adversarial Network, and then use this methodology to train a NMT system on unpaired data. Our second technique converts sequences into a tree-structured representation, and performs translation from tree-to-tree. This improves the handling of very long sequences since it reduces the distance between nodes in the network, and allows the network to take advantage of information contained in the tree structure to reduce overfitting.en_US
dc.language.isoen_US
dc.rightsAttribution 4.0 Internationalen_US
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectComputer scienceen_US
dc.subjectGenerative adversarial networksen_US
dc.subjectMachine learningen_US
dc.subjectNatural language processingen_US
dc.titleImproved neural machine translation systems for low resource correction tasksen_US
dc.typeThesis/Dissertationen_US
dc.date.updated2020-02-14T20:02:03Z
etd.degree.nameDoctor of Philosophyen_US
etd.degree.leveldoctoralen_US
etd.degree.disciplineComputer Scienceen_US
etd.degree.grantorBoston Universityen_US
dc.identifier.orcid0000-0003-3174-1824


This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's license is described as Attribution 4.0 International