Syntactic Reordering in Preprocessing for JapaneseEnglish Translation: MIT System Description for NTCIR-7 Patent Translation Task

Abstract

We experimented with a well-known technique of training a JapaneseEnglish translation system on a Japanese training corpus that has been reordered into an English-like word order. We achieved sur-prisingly impressive results by naively reordering each Japanese sentence into reverse order. We also de-veloped a reordering algorithm that transforms a Japanese dependency parse into English word order.