The paper describes the construction of a lexical transducer for Korean that can be used for stemming and generation. The method contains two innovations: (1) two h.'vel rule...
We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
We show that for every deterministic bottom-up tree transducer, a unique equivalent transducer can be constructed which is minimal. The construction is based on a sequence of norma...
This paper describes a new method for building compact context-dependency transducers for finite-state transducer-based ASR decoders. Instead of the conventional phonetic decision...