A Rule Based Machine Translation Scheme from Greek to Greek Sign Language: Production of Different Types of Large Corporations

One of the aims of Assistive Technologies is to help people with disabilities to communicate withothers and to provide means of access to information. As an aid to Deaf people, in this work we present a novelprototype Rule Based Machine Translation (RBMT) system for the creation of large quality written Greek SignLanguage (GSL) glossed corpora. In particular, the proposed RBMT system supports the professional translatorof GSL to produce different kinds of GSL glossed corpus. Evaluation of the proposed scheme is carried out forthe weather reports domain, were 20,284 tokens and 1,000 sentences have been produced. By using theBiLingual Evaluation Understudy (BLEU) metric score [32], our prototyped RBMT system achieves arelative score of 84% for 4-gram evaluation and 90% for 1-gram