Bidirectional Machine Translation Between Turkish and Turkish Sign Language : A Data-Driven Approach

Abstract

Communication is one of the first necessities for human beings to live and survive. There are many different ways to communicate for centuries, yet there are mainly three ways for today's world: spoken, written and sign languages. According to research on the language usage of deaf people, they commonly prefer sign language over other ways. Most of the times they need helpers and/or interpreters on daily life and they are accompanied by human helpers. We intend to make a bidirectional dynamic machine translation system by using an example-based approach, and apply between Turkish and Turkish Sign Language (TSL) glosses for the first time in literature with the belief of one day this novel work on Turkish would help these people to live independently. Using BLEU and TER metrics for evaluation, we tested our system considering many conditions, and got competitive results especially compared to previous work in this field.