Memory-Based Machine Translation and Language Modeling

Abstract

Memory-Based Machine Translation and Language Modeling 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 source-language 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. The system is released as an open source software package 1 , for which we provide a first reference guide.