Effects of Parsing Errors on Pre-Reordering Performance for Chinese-to-Japanese SMT

Linguistically motivated reordering methods have been developed to improve word alignment especially for Statistical Machine Translation (SMT) on long distance language pairs. However, since they highly rely on the parsing accuracy, it is useful to explore the relationship between parsing and reordering. For Chinese-toJapanese SMT, we carry out a three-stage incremental comparative analysis to observe the effects of different parsing errors on reordering performance by combining empirical and descriptive approaches. For the empirical approach, we quantify the distribution of general parsing errors along with reordering qualities whereas for the descriptive approach, we extract seven influential error patterns and examine their correlation with reordering errors.