Tree Transducers, Machine Translation, and Cross-Language Divergences
This work addresses structural translation challenges for machine translation systems, but it is incremental as it builds on existing formalisms and reviews known methods.
The paper tackles the problem of handling cross-language structural divergences in machine translation by using tree transducers, specifically T and xT transducers, to implement translation rules that cover all divergences described in Bonnie Dorr's work, and presents an implementation for experimentation.
Tree transducers are formal automata that transform trees into other trees. Many varieties of tree transducers have been explored in the automata theory literature, and more recently, in the machine translation literature. In this paper I review T and xT transducers, situate them among related formalisms, and show how they can be used to implement rules for machine translation systems that cover all of the cross-language structural divergences described in Bonnie Dorr's influential article on the topic. I also present an implementation of xT transduction, suitable and convenient for experimenting with translation rules.