The Universal Parser Compiler and Its Application to a Speech Translation System

We describe our Universal Parser Architecture and its use in a speech translation system, based on the Machine Translation system under development at the Center for Machine Translation at Carnegie Mellon. To "understand" natural language, a system must have syntactic knowledge of the language and semantic knowledge of the domain. The Universal Parser Architecture allows grammar writers to develop these kinds of knowledge separately in a declarative manner, and the compiler/interpreter integrates these two knowledge bases dynamically in order to parse input sentences. We recently integrated our system with a speech recognition system to accept spoken sentences (rather than typed sentences) by extending our runtime parser component to handle "noisy" phoneme sequences (of spoken utterances) that possibly include recognition errors. The nature of this modification is explained and examples are presented. We find our architecture very suitable for speech translation, as it combines the use of domain semantic knowledge with a highly efficient runtime parsing algorithm, thus accommodating the increased search space necessary for parsing speech input. Published in the Proceedings of the Second International Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages, at Carnegie-Mellon University in Pittsburgh, Pennsylvania, June, 1988. 1 Some portions of this paper are taken from the following papers: "Linguistic and Domain Knowledge Sources for the Universal Parser Architecture" by Tomita, M., Kee, M., Mitamura, T. and Carbonell, J. G.; in Terminology and Knowledge Engineering. INDEKS Verlag, Frankfurt/M., 1987 "Parsing Noisy Sentences" by Saito, H. and Tomita, M.; in proceedings of COLING88, Budapest, 1988 We should also like to thank other members of the Center for Machine Translation for useful comments and advice. Funding for this project is provided by several private institutions and governmental agencies in the United States and Japan. Table of