Cross-lingual learning in low-resource : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science, School of Natural and Computational Sciences, Massey University, Auckland, New Zealand

Simple item page
dc.confidentialEmbargo : Noen_US
dc.contributor.advisorAndrew, Gilman
dc.contributor.authorZhao, Jiawei
dc.date.accessioned2022-05-09T00:00:47Z
dc.date.accessioned2022-08-29T00:29:20Z
dc.date.available2022-05-09T00:00:47Z
dc.date.available2022-08-29T00:29:20Z
dc.date.issued2022
dc.descriptionJiawei Zhaoen_US
dc.description.abstractCurrent machine translation techniques were developed using predominantly rich resource language pairs. However, there is a broader range of languages used in practice around the world. For instance, machine translation between Finnish, Chinese and Russian is still not suitable for high-quality communication. This dissertation focuses on building cross-lingual models to address this issue. I aim to analyse the relationships between embeddings of different languages, especially low-resource languages. I investigate four phenomena that can improve the translation of low-resource languages. The first study concentrates on the non-linearity of cross-lingual word embeddings. Current approaches primarily focus on linear mapping between the word embeddings of different languages. However, those approaches don't seem to work as well with some language pairs, mostly if the two languages belong to different language families, e.g. English and Chinese. I hypothesise that linearity, which is often assumed in the geometric relationship between monolingual word embeddings of different languages, may not hold for all language pairs. I focus on investigating the relationship between word embeddings of languages in different language families. I show that non-linearity can better describe the relationship in those language pairs using multiple datasets. The second study focuses on the unsupervised cross-lingual word embeddings for low-resource languages. Conventional approach to constructing cross-lingual word embeddings requires a large dictionary, which is hard to obtain for low-resource languages. I propose an unsupervised approach to learning cross-lingual word embeddings for low-resource languages. By incorporating kernel canonical correlation analysis, the proposed approach can better learn high-quality cross-lingual word embeddings in an unsupervised scenario. The third study investigates a dictionary augmentation technique for low-resource languages. A key challenge for constructing an accurately augmented dictionary is the high variance issue. I propose a semi-supervised method that can bootstrap a small dictionary into a larger high-quality dictionary. The fourth study concentrates on the data insufficiency issue in speech translation. The lack of training data availability for low-resource languages limits the performance of end-to-end speech translation. I investigate the use of knowledge distillation to transfer knowledge from the machine translation task to the speech translation task and propose a new training methodology. The results and analyses presented in this work show that a wide range of techniques can address issues that arise with low-resource languages in the machine translation field. This dissertation provides a deeper insight into understanding the word representations and structures in low-resource translation and should aid future researchers to better utilise their translation models.en
dc.identifier.urihttp://hdl.handle.net/10179/17517
dc.publisherMassey Universityen_US
dc.rightsThe Authoren_US
dc.subjectMachine learningen
dc.subjectNatural language processing (Computer science)en
dc.subjectMachine translatingen
dc.subject.anzsrc460208 Natural language processingen
dc.titleCross-lingual learning in low-resource : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science, School of Natural and Computational Sciences, Massey University, Auckland, New Zealanden_US
dc.typeThesisen_US
massey.contributor.authorZhao, Jiaweien_US
thesis.degree.disciplineComputer Scienceen_US
thesis.degree.grantorMassey Universityen_US
thesis.degree.levelDoctoralen_US
thesis.degree.nameDoctor of Philosophy (PhD)en_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ZhaoPhDThesis.pdf
Size:
5.51 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Theses and Dissertations