Learning with Weighted Transducers

Weighted finite-state transducers have been used successfully in a variety of natural language processing applications, including speech recognition, speech synthesis, and machine translation. This paper shows how weighted transducers can be combined with existing learning algorithms to form powerful techniques for sequence learning problems. Keywords. Learning, kernels, classification, regression, ranking, clustering, weighted automata, weighted transducers, rational powers series.

• Type: Conference
• Year: 2008
• Where: FSMNLP
• Authors: Corinna Cortes, Mehryar Mohri
• Keywords: Finite-state Transducers, FSMNLP 2008, Natural Language Processing, Weighted Automata, Weighted Transducers