A Novel Approach for Translating English Statements to American Sign Language Gloss

摘要

In this paper, we present a study on the relationship between American Sign Language (ASL) statements and English written texts toward building a statistical machine translation (SMT) using 3D avatar for interpretation. The process included a novel algorithm which transforms an English part-of-speech sentence to ASL-Gloss. The algorithm uses a rule-based approach for building big parallel corpus from English to ASL-Gloss using dependency rules of grammatical parts of the sentence. The parallel corpus will be the input of the translation model of the SMT for ASL. The results we obtained are highly consistent, reproducible, with fairly high precision and accuracy.