Abstract

We describe a freely available open source memory-based machine translation system, mbmt. Its translation model is a fast approximate memory-based classifier, trained to map trigrams of sourcelanguage words onto trigrams of target-language words. In a second decoding step, the predicted trigrams are rearranged according to their overlap, and candidate output sequences are ranked according to a memory-based language model. We report on the scaling abilities of the memory-based approach, observing fast training and testing times, and linear scaling behavior in speed and memory costs. �e system is released as an open source so�ware package, for which we provide a first reference guide. 1.

Citations