Machine learning of language translation rules
Jarno Tenni, Aarno Lehtola, Catherine Bounsaythip, Kristiina Jaaranen · 2003
The purpose of this paper is to present learning methods for creating language translation rules from multilingual text samples. The languages concerned are controlled languages, i.e., they are domain specific sublanguages with ambiguities eliminated by restricting the vocabulary and syntax. Learning methods presented here enable a supervised, human-assisted learning of generalised translation rules, thus making it faster and easier to adapt our machine translation system to new languages.