Abstract
The most salient feature of a knowledge-based machine translation system is its reliance on understanding (and representing in a specially designed artificial meaning representation language, interlingua) the meaning of an input text. DIONYSUS, the KBMT system developed at CMU, is a combination of two research projects — the DIOGENES natural language generation project and the DIANA natural language understanding project. Meaning analysis in DIONYSUS takes into account both the semantics and the pragmatics of the input text. The result of the semantic and pragmatic analysis is called interlingua text or ILT, which is a text in a specially designed text meaning representation language TAMERLAN (Nirenburg and Defrise, 1991). Most semantic elements of meaning are produced by instantiating tokens of concepts from an underlying ontological and domain model (called concept lexicon in the KBMT-89 machine translation system, an earlier system we developed, see Goodman, 1989). The pragmatic elements of meaning are determined through various lexical and syntactic clues in the input, largely independently from the domain model.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
