Machine Translation with Inferred Stochastic Finite-State Transducers

Machine Translation with Inferred Stochastic Finite-State Transducers

Finite-state transducers are models that are being used in different areas of pattern recognition and computational linguistics. One of these areas is machine translation, in which the approaches that are based on building models automatically from training examples are becoming more and more attractive. Finite-state transducers are very adequate for use in constrained tasks in which training s...

Linguistic Categorisation in Machine Translation using Stochastic Finite State Transducers

In the last years, statistical machine translation has already demonstrated its usefulness within a wide variety of translation applications. In particular, finite state models are always an interesting framework because there are well-known efficient algorithms for their representation and manipulation. Nevertheless, statistical approaches have rarely been performed taking into account the lin...

Large-Scale Statistical Machine Translation with Weighted Finite State Transducers

The Cambridge University Engineering Department phrasebased statistical machine translation system follows a generative model of translation and is implemented by the composition of component models of translation and movement realised as Weighted Finite State Transducers. Our flexible architecture requires no special purpose decoder and readily handles the large-scale natural language processi...

Basque-spanish-english Machine Translation Using Finite-state Transducers

The goals of this work are, on the one hand to develop a trilingual corpus suitable for example-based text and speech-input machine translation between English, Spanish and Basque; and on the other hand, to compare the same translation method for under two very different pair of languages: Spanish-Basque and Spanish-English. The stochastic finite-state transducers have been trained from raw bil...

Translation with Cascaded Finite State Transducers