A prototype system for machine translation from English to South African Sign Language using synchronous tree adjoining grammars

[摘要] ENGLISH ABSTRACT: Machine translation, especially machine translation for sign languages, remains an active researcharea. Sign language machine translation presents unique challenges to the whole machine translationprocess. In this thesis a prototype machine translation system is presented. This system isdesigned to translate English text into a gloss based representation of South African Sign Language(SASL).In order to perform the machine translation, a transfer based approach was taken. Englishtext is parsed into an intermediate representation. Translation rules are then applied to thisintermediate representation to transform it into an equivalent intermediate representation for theSASL glosses. For both these intermediate representations, a tree adjoining grammar (TAG)formalism is used. As part of the prototype machine translation system, a TAG parser wasimplemented.The translation rules used by the system were derived from a SASL phrase book. This phrasebook was also used to create a small gloss based SASL TAG grammar. Lastly, some additionaltools, for the editing of TAG trees, were also added to the prototype system.

[发布机构] Stellenbosch University