Rapid Prototyping of a Transfer-based Hebrew-to-English
Machine Translation System
Alon Lavie, Erik Peterson, Katharina Probst
Language Technologies Institute
Carnegie Mellon University
email: alavie@cs.cmu.edu
Shuly Wintner, Yaniv Eytani
Department of Computer Science
University of Haifa
email: shuly@cs.haifa.ac.il
Abstract
We describe the rapid development of a preliminary Hebrew-to-English Machine Translation
system under a transfer-based framework specifically designed for rapid MT prototyping for lan-
guages with limited linguistic resources. The task is particularly challenging due to two main rea-
sons: the high lexical and morphological ambiguity of Hebrew and the dearth of available resources
for the language. Existing, publicly available resources were adapted in novel ways to support the
MT task. The methodology behind the system combines two separate modules: a transfer engine
which produces a lattice of possible translation segments, and a decoder which searches and selects
the most likely translation according to an English language model. We demonstrate that a small
manually crafted set of transfer rules suffices to produce legible translations. Performance results
are evaluated using state of the art measures and are shown to be encouraging.
1 Introduction
Machine translation of Hebrew is challenging due to two main reasons: the high lexical and morpholog-
ical ambiguity of Hebrew and its orthography, and the paucity of available resources for the language. In
this paper we describe the rapid development of a preliminary Hebrew-to-English Machine Translation
system under a transfer-based framework specifically designed for rapid MT prototyping for languages
with limited linguistic resources. The system was developed over the course of a two-month period with
a total labor-effort equivalent to about four person-months of development. To the best of our knowl-
edge, our system is the first broad-domain machine translation system for Hebrew. We used existing,
publicly available resources which we ada