Tree Transducers, Machine Translation, and Cross-Language Divergences

TL;DR

This paper reviews tree transducers, especially T and xT types, and demonstrates their application in handling cross-language structural divergences in machine translation, providing a practical implementation for experimentation.

Contribution

It offers a comprehensive review of tree transducers and introduces an implementation of xT transduction for machine translation rule experiments.

Findings

xT transducers effectively model cross-language divergences

Implementation facilitates experimentation with translation rules

Framework unifies formal automata and practical translation applications

Abstract

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.