Can the Internet help improve Machine Translation?

This paper summarizes a largely automated method that uses online post-editing feedback to automatically improve translation rules. As a starting point, bilingual speakers’ local fixes are collected through an online Translation Correction Tool. Next, the Rule Refinement Module attacks the problem at its core and uses the local fixes to detect incorrect rules that need to be refined. Once the grammar and lexicon have been refined, the Machine Translation system not only produces the correct translation as fixed by the bilingual speaker, but is also able to generalize and correctly translates similar sentences. Thus, this work constitutes a novel approach to improving translation quality. Enhanced by the reaching power of the Internet, our approach becomes even more relevant to address the problem of how to automatically improve the quality of Machine Translation output.