Spectral Clustering for Example-Based Machine Translation

Prior work has shown that generalization of data in an Example Based Machine Translation (EBMT) system, reduces the amount of pre-translated text required to achieve a certain level of accuracy (Brown, 2000). Several word clustering algorithms have been suggested to perform these generalizations, such as k-Means clustering or Group Average Clustering. The hypothesis is that better contextual clustering can lead to better translation accuracy with limited training data. In this paper, we use a form of spectral clustering to cluster words, and this is shown to result in as much as 29.08% improvement over the baseline EBMT system.