International Workshop on Spoken Language Translation (IWSLT) 2006

Keihanna Science City, Kyoto, Japan
November 27-28, 2006

Finite-State Transducer-based Statistical Machine Translation using Joint Probabilities

Srinivas Bangalore, Stephan Kanthak, Patrick Haffner

AT&T Labs-Research, Florham Park, NJ, USA

In this paper, we present our system for statistical machine translation that is based on weighted finite-state transducers. We describe the construction of the transducer, the estimation of the weights, acquisition of phrases (locally ordered tokens) and the mechanism we use for global reordering. We also present a novel approach to machine translation that uses a maximum entropy model for parameter estimation and contrast its performance to the finite-state translation model on the IWSLT Chinese-English data sets.

Full Paper     Presentation

Bibliographic reference.  Bangalore, Srinivas / Kanthak, Stephan / Haffner, Patrick (2006): "Finite-state transducer-based statistical machine translation using joint probabilities", In IWSLT-2006, 16-22.