Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Resourcing machine translation with parallel treebanks

Tinsley, John (2010) Resourcing machine translation with parallel treebanks. PhD thesis, Dublin City University.

Abstract
The benefits of syntax-based approaches to data-driven machine translation (MT) are clear: given the right model, a combination of hierarchical structure, constituent labels and morphological information can be exploited to produce more fluent, grammatical translation output. This has been demonstrated by the recent shift in research focus towards such linguistically motivated approaches. However, one issue facing developers of such models that is not encountered in the development of state-of-the-art string-based statistical MT (SMT) systems is the lack of available syntactically annotated training data for many languages. In this thesis, we propose a solution to the problem of limited resources for syntax-based MT by introducing a novel sub-sentential alignment algorithm for the induction of translational equivalence links between pairs of phrase structure trees. This algorithm, which operates on a language pair-independent basis, allows for the automatic generation of large-scale parallel treebanks which are useful not only for machine translation, but also across a variety of natural language processing tasks. We demonstrate the viability of our automatically generated parallel treebanks by means of a thorough evaluation process during which they are compared to a manually annotated gold standard parallel treebank both intrinsically and in an MT task. Following this, we hypothesise that these parallel treebanks are not only useful in syntax-based MT, but also have the potential to be exploited in other paradigms of MT. To this end, we carry out a large number of experiments across a variety of data sets and language pairs, in which we exploit the information encoded within the parallel treebanks in various components of phrase-based statistical MT systems. We demonstrate that improvements in translation accuracy can be achieved by enhancing SMT phrase tables with linguistically motivated phrase pairs extracted from a parallel treebank, while showing that a number of other features in SMT can also be supplemented with varying degrees of effectiveness. Finally, we examine ways in which synchronous grammars extracted from parallel treebanks can improve the quality of translation output, focussing on real translation examples from a syntax-based MT system.
Metadata
Item Type:Thesis (PhD)
Date of Award:March 2010
Refereed:No
Additional Information:Developed as part of Prof. Way's 'ATTEMPT' project, a basic research project funded by SFI, grant number 06/RF/CMS064.
Supervisor(s):Way, Andy
Subjects:Computer Science > Computational linguistics
Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > National Centre for Language Technology (NCLT)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 3.0 License. View License
Funders:Science Foundation Ireland
ID Code:15071
Deposited On:31 Mar 2010 13:37 by Andrew Way . Last Modified 23 Oct 2019 14:29
Documents

Full text available as:

[thumbnail of JohnThesis.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record