Handling Translation Divergences: Combining Statistical and Symbolic Techniques in Generation-Heavy Machine Translation (2002)
| Venue: | In Fifth Conference of the Association for Machine Translation in the Americas, AMTA-2002 |
| Citations: | 16 - 5 self |
BibTeX
@INPROCEEDINGS{Habash02handlingtranslation,
author = {Nizar Habash and Bonnie Dorr},
title = {Handling Translation Divergences: Combining Statistical and Symbolic Techniques in Generation-Heavy Machine Translation},
booktitle = {In Fifth Conference of the Association for Machine Translation in the Americas, AMTA-2002},
year = {2002},
pages = {84--93}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper describes a novel approach to handling translation divergences in a Generation-Heavy Hybrid Machine Translation (GHMT) system. The translation divergence problem is usually reserved for Transfer and Interlingual MT because it requires a large combination of complex lexical and structural mappings. A major requirement of these approaches is the accessibility of large amounts of explicit symmetric knowledge for both source and target languages. This limitation renders Transfer and Interlingual approaches ineffective in the face of structurally-divergent language pairs with asymmetric resources. GHMT addresses the more common form of this problem, source-poor/targetrich, by fully exploiting symbolic and statistical target-language resources.
