Cross modal comprehension in ZARDOZ an English to sign-language translation system

摘要: The sign languages used by deaf communities around the world represent a linguistic challenge that natural language researchers have only recently begun to take up. Zardoz is system which tackles cross-modal machine-translation problem, translating speech and text into animated language. Native languages, such as ISL (Ireland), BSL (Britain) ASL (U.S.A.) evolved in methods of gestural communication. These differ from English, not modality, but grammatical structure, exploiting dimensions space well time. This paper presents an architectural overview Zardoz, describes employed analyse verbal input generate corresponding signed output.