Designing High Accuracy Statistical Machine Translation for Sign Language Using Parallel Corpus

Abstract

In this article, the authors deal with the machine translation of written English text to sign language. They study the existing systems and issues in order to propose an implantation of a statistical machine translation from written English text to American Sign Language (English/ASL) taking care of several features of sign language. The work proposes a novel approach to build artificial corpus using grammatical dependencies rules owing to the lack of resources for sign language. The parallel corpus was the input of the statistical machine translation, which was used for creating statistical memory translation based on IBM alignment algorithms. These algorithms were enhanced and optimized by integrating the Jaro–Winkler distances in order to decrease training process. Subsequently, based on the constructed translation memory, a decoder was implemented for translating English text to the ASL using a novel proposed transcription system based on gloss annotation. The results were evaluated using the BLEU evaluation metric.