Automatic Error Analysis for Morphologically Rich Languages
Ahmed El Kholy, Nizar Y. Habash · 2011
This paper presents AMEANA, an opensource tool for error analysis for natural language processing tasks targeting morphologically rich languages. Unlike standard evaluation metrics such as BLEU or WER, AMEANA automatically provides a detailed error analysis that can help researchers and developers better understand the strengths and weaknesses of their systems. AMEANA is easily adaptable to any language provided the existence of a morphological analyzer. In this paper, we focus on usability in the context of Machine Translation (MT) and demonstrate it specifically for English-to-Arabic MT.