An Open-Source Finite State Morphological Transducer for Modern

We develop an open-source large-scale finite-state morphological processing toolkit (Ara-ComLex) for Modern Standard Arabic (MSA) distributed under the GPLv3 license.1 The morphological transducer is based on a lexi-cal database specifically constructed for this purpose. In contrast to previous resources, the database is tuned to MSA, eliminating lexi-cal entries no longer attested in contemporary use. The database is built using a corpus of 1,089,111,204 words, a pre-annotation tool, machine learning techniques, and knowledge-based pattern matching to automatically ac-quire lexical knowledge. Our morphologi-cal transducer is evaluated and compared to LDC’s SAMA (Standard Arabic Morphologi-cal Analyser)