Back to search

Boston University

Improved neural machine translation systems for low resource correction tasks

Abstract

dc:description.abstract

Recent 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.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Computer Science
Grantor
Boston University
Year dc:date.issued
2019

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Harer, Jacob Alexander
Advisor dc:contributor.advisor
  • Chin, Sang
ORCID dc:identifier.orcid

Subjects

dc:subject × 4

Rights

dc:rights
Statement dc:rights
  • Attribution 4.0 International
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/2144/39550

Chain of custody

source
Harvested from
Boston University
Base URL
open.bu.edu/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Harer, Jacob Alexander. Improved neural machine translation systems for low resource correction tasks. doctoral thesis, Boston University, 2019. https://hdl.handle.net/2144/39550