Marker-Based Chunking in Eleven European Languages for Analogy-Based Translation

摘要

An example-based machine translation (EBMT) system based on proportional analogies requires numerous proportional analogies between linguistic units to work properly. Consequently, long sentences cannot be handled directly in such a framework. Cutting sentences into chunks would be a solution. Using different markers, we count the number of proportional analogies between chunks in 11 European languages. As expected, the number of proportional analogies between chunks found is very high. These results, and preliminary experiments in translation, are promising for the EBMT system that we intend to build.