Adrià de Gispert,

University of Cambridge

Abstract:

In this talk I will describe HiFST, the Cambridge University Engineering Department statistical machine translation system. I will review hierarchical-phrase based translation, and explain why an implementation based on Weighted Finite-State Transducers is convenient to avoid search errors in decoding.

I will then give an overview of the current research lines of our SMT group, focused on defining appropriate translation grammars, exploiting the vast number of alternative hypotheses encoded in translation lattices via restoring with large-scale language models, and decoding under Minimum Bayes Risk for system combination.

 

Date: 2010-Jul-20     Time: 14:00:00     Room: Room FA1 – Pavilhão de Informática I (IST)


For more information: