Enhancing Machine Translation for English-Japanese Using Syntactic Pattern Recognition Methods
Public Deposited- Resource Type
- Creator
- Abstract
In this thesis, we present a novel approach to machine translation using syntactic Pattern Recognition (PR) methods. The purpose of this research is to evaluate the possibility of using syntactic PR techniques in this field. To make use of syntactic PR techniques, we propose a system that performs string-matching to pair English sentence structures to Japanese structures. In order to process the sentence structures of either language as a string, we have created a representation that replaces the tokens of a sentence with their respective Part-of-Speech tags. To perform the string-matching operation we make use of the OptPR algorithm, a syntactic PR scheme that has been proven to achieve optimal accuracy. Through our experiments, we show that our implementation obtains superior results to that of a standard statistical machine translation system on our data set, with the additional guarantee of generating a known sentence structure.
- Subject
- Language
- Publisher
- Thesis Degree Level
- Thesis Degree Name
- Thesis Degree Discipline
- Identifier
- Rights Notes
Copyright © 2015 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Date Created
- 2015
Relations
- In Collection:
Items
Thumbnail | Title | Date Uploaded | Visibility | Actions |
---|---|---|---|---|
mcmahon-enhancingmachinetranslationforenglishjapanese.pdf | 2023-05-04 | Public | Download |