A Hierarchical Phrase-Based Model for English-Persian Statistical Machine Translation

Loading...
Thumbnail Image

Supplementary material

Other Title

Author ORCID Profiles (clickable)

Degree

Grantor

Date

Supervisors

Ngā Upoko Tukutuku (Māori subject headings)

Keyword

statistical machine translation (SMT)
natural language generation (computer science)
hierarchical phrase-based models

Citation

Mohaghegh, M., and Sarrafzadeh, H. (2012). A Hierarchical Phrase-Based Model for English-Persian Statistical Machine Translation. Innovations 12, 8th International Conference on Innovations in Information Technology. 18-20 March. pp. 205-208. doi: 10.1109/INNOVATIONS.2012.6207733.

Abstract

In this paper we show that a hierarchical phrasebased translation system will outperform a classical (nonhierarchical) phrase-based system in the English-to-Persian translation direction, yet for the Persian-to-English direction, the classical phrase-based system is preferable. We seek to explain why this is so, and detail a series of translation experiments with our SMT system using various bilingual corpora each with both toolkits Moses (non-hierarchical) and Joshua (hierarchical).

Publisher

Link to ePress publication

DOI

10.1109/INNOVATIONS.2012.6207733

Copyright holder

Authors

Copyright notice

All rights reserved

Copyright license

Available online at

This item appears in: