Rich Morphology Generation Using Statistical Machine Translation
Ahmed El Kholy, Nizar Y. Habash · 2012
We present an approach for generation of morphologically rich languages using statistical machine translation. Given a sequence of lemmas 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. 1