Automatic learning of word transducers from examples

Open Access
Publisher Website
Google Scholar
Abstract
This paper describes the application of markovian learning methods to the inference of word transducers. We show how the proposed method dispenses from the difficult design of hand-crafted rules, allows the use of weighed non deterministic transducers and is able to translate words by taking into account their whole rather than by making decisions locally. These arguments are illustrated on two examples: morphological analysis and grapheme-to-phoneme transcription.

This publication has 0 references indexed in Scilit: