All in Strings: a Powerful String-based Automatic MT Evaluation Metric with Multiple Granularities

String-based metrics of automatic machine translation (MT) evaluation are widely applied in MT research. Meanwhile, some linguistic motivated metrics have been suggested to improve the string-based metrics in sentencelevel evaluation. In this work, we attempt to change their original calculation units (granularities) of string-based metrics to generate new features. We then propose a powerful string-based automatic MT evaluation metric, combining all the features with various granularities based on SVM rank and regression models. The experimental results show that i) the new features with various granularities can contribute to the automatic evaluation of translation quality; ii) our proposed string-based metrics with multiple granularities based on SVM regression model can achieve higher correlations with human assessments than the stateof-art automatic metrics.