Increasing the throughput of machine translation systems using clouds

TL;DR

This paper demonstrates that implementing machine translation systems within the MapReduce framework can significantly increase throughput without sacrificing translation quality, applicable to both rule-based and statistical paradigms.

Contribution

It introduces a novel approach of using MapReduce for machine translation, showing improved throughput while maintaining output quality.

Findings

MapReduce can successfully increase translation system throughput

The approach works for both Rule-Based and Statistical Machine Translation

Translation quality remains unaffected by the MapReduce implementation

Abstract

The manuscript presents an experiment at implementation of a Machine Translation system in a MapReduce model. The empirical evaluation was done using fully implemented translation systems embedded into the MapReduce programming model. Two machine translation paradigms were studied: shallow transfer Rule Based Machine Translation and Statistical Machine Translation. The results show that the MapReduce model can be successfully used to increase the throughput of a machine translation system. Furthermore this method enhances the throughput of a machine translation system without decreasing the quality of the translation output. Thus, the present manuscript also represents a contribution to the seminal work in natural language processing, specifically Machine Translation. It first points toward the importance of the definition of the metric of throughput of translation system and, second, the applicability of the machine translation task to the MapReduce paradigm.