A preprocessor for an English-to-Sign Language Machine Translation system

[摘要] Sign Languages such as South African Sign Language, are proper natural languages;they have their own vocabularies, and they make use of their own grammarrules.However, machine translation from a spoken to a signed language creates interestingchallenges. These problems are caused as a result of the differences incharacter between spoken and signed languages. Sign Languages are classified asvisual-spatial languages: a signer makes use of the space around him, and givesvisual clues from body language, facial expressions and sign movements to helphim communicate. It is the absence of these elements in the written form of aspoken language that causes the contextual ambiguities during machine translation.The work described in this thesis is aimed at resolving the ambiguities causedby a translation from written English to South African Sign Language. Wedesigned and implemented a preprocessor that uses areas of linguistics such asanaphora resolution and a data structure called a scene graph to help with thespatial aspect of the translation. The preprocessor also makes use of semanticand syntactic analysis, together with the help of a semantic relational database,to find emotional context from text. This analysis is then used to suggest bodylanguage, facial expressions and sign movement attributes, helping us to addressthe visual aspect of the translation.The results show that the system is flexible enough to be used with differenttypes of text, and will overall improve the quality of a machine translation fromEnglish into a Sign Language.

[发布机构] Stellenbosch University