Aspect Marker Generation in English-to-Chinese Machine Translation

This paper reports on a pilot study of aspect marker generation in an English-to-Chinese translation scenario. Our classifier combines a number of linguistic features in a Maximum Entropy framework and achieves an overall accuracy of 78%. We also investigate the impact of different clusters of linguistic features; we find that syntactic features have the highest utility and lexical aspectual properties associated with verbs do not have significant contribution to the prediction of aspect markers. Furthermore, we have demonstrated converging evidence that there is only marginal sequential dependency between the aspect markers of different verbs in the same sentence.