Challenges in building an Arabic-English GHMT system with SMT components

TitleChallenges in building an Arabic-English GHMT system with SMT components
Publication TypeJournal Articles
Year of Publication2006
AuthorsHabash N, Dorr BJ, Monz C
JournalProceedings of the 11th Annual Conference of the European Association for Machine Translation (EAMT-2006)
Pagination56 - 65
Date Published2006///
Abstract

The research context of this paper is de-veloping hybrid machine translation (MT)
systems that exploit the advantages of
linguistic rule-based and statistical MT
systems. Arabic, as a morphologically
rich language, is especially challenging
even without addressing the hybridiza-
tion question. In this paper, we describe
the challenges in building an Arabic-
English generation-heavy machine trans-
lation (GHMT) system and boosting it
with statistical machine translation (SMT)
components. We present an extensive
evaluation of multiple system variants and
report positive results on the advantages of
hybridization.