Enriching Morphologically Poor Languages for Statistical Machine Translation

Eleftherios Avramidis, Philipp Koehn

In: Proceedings of ACL-08: HLT. Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT-08) June 15-20 Columbus Ohio United States Pages 763-770 Association for Computational Linguistics 6/2008.


We address the problem of translating from morphologically poor to morphologically rich languages by adding per-word linguistic information to the source language. We use the syntax of the source sentence to extract information for noun cases and verb persons and annotate the corresponding words accord ingly. In experiments, we show improved performance for translating from English into Greek and Czech. For English–Greek, we reduce the error on the verb conjugation from 19% to 5.4% and noun case agreement from 9% to 6%.

Weitere Links

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz