Paper: Weighted Rational Transductions And Their Application To Human Language Processing

ACL ID H94-1050
Title Weighted Rational Transductions And Their Application To Human Language Processing
Venue Human Language Technologies
Session Main Conference
Year 1994
Authors

We present the concepts of weighted language, ~ansduction and au- tomaton from algebraic automata theory as a general framework for describing and implementing decoding cascades in speech and lan- guage processing. This generality allows us to represent uniformly such information sources as pronunciation dictionaries, language models artd lattices, and to use uniform algorithms for building de- coding stages and for optimizing and combining them. In particular, a single automata join algorithm can be used either to combine in- formation sources such as a pronunciation dictionary and a context- dependency model during the construction of a decoder, or dynam- ically during the operation of the decoder. Applications to speech recognition and to Chinese text segmentation will be discussed.