Paper: Rich Morphology Generation Using Statistical Machine Translation

ACL ID W12-1514
Title Rich Morphology Generation Using Statistical Machine Translation
Venue International Conference on Natural Language Generation
Session Main Conference
Year 2012
Authors

We present an approach for generation of mor- phologically rich languages using statistical machine translation. Given a sequence of lem- mas and any subset of morphological features, we produce the inflected word forms. Testing on Arabic, a morphologically rich language, our models can reach 92.1% accuracy starting only with lemmas, and 98.9% accuracy if all the gold features are provided.