Our submission is a non-structural Example-Based Machine Translation system that translates text from Arabic to English, using a parallel corpus aligned at the paragraph / sentence level. Each new input sentence is fragmented into phrases and those phrases are matched to example patterns, using various levels of morphological information. Source-language synonyms were derived automatically and used to help locate potential translation examples for fragments of a given input sentence. We participated in the BTEC task for translating Arabic sentences to English.
Cite as: Bar, K., Dershowitz, N. (2010) Tel aviv university's system description for IWSLT 2010. Proc. International Workshop on Spoken Language Translation (IWSLT 2010), 169-174
@inproceedings{bar10_iwslt,
author={Kfir Bar and Nachum Dershowitz},
title={{Tel aviv university's system description for IWSLT 2010}},
year=2010,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2010)},
pages={169--174}
}