SYSTRAN's Chinese Word Segmentation

Abstract

SYSTRAN's Chinese word segmentation is one important component of its Chinese-English machine translation system. The Chinese word segmentation module uses a rule-based approach, based on a large dictionary and fine-grained linguistic rules. It works on general-purpose texts from different Chinese-speaking regions, with comparable performance. SYSTRAN participated in the four open tracks in the First International Chinese Word Segmentation Bakeoff. This paper gives a general description of the segmentation module, as well as the results and analysis of its performance in the Bakeoff.