Year: 2008
Type: conference-paper
Abstract: In this paper, we present a novel morphology preprocessing technique for Arabic-English translation. We exploit the Arabic morphology-English alignment to learn a model removing nonaligned Arabic morphemes. The model is an instance of the Conditional Random Field (Lafferty et al., 2001) model; it deletes a morpheme based on the morpheme's context. We achieved around two BLEU points improvement over the original Arabic translation for both a travel-domain system trained on 20K sentence pairs and a news domain system trained on 177K sentence pairs, and showed a potential improvement for a large-scale SMT system trained on 5 million sentence pairs.
Authors: ThuyLinh Nguyen, Stephan Vogel
Institution: Carnegie Mellon University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2158678029