NEC Corporat ion and University of Sheffield: "Description of NEC/Shef f le ld System Used For MET Japanese"

been studied as a part of the more general problem of morphological nalysis in Japanese text processing ([1] [2]). It has also been studied in the framework of Japanese information extraction ([3]) in recent years. Our approach to the Multi-lingual Evaluation Task (MET) for Japanese text is to consider the given task as a morphological nalysis problem in Japanese. Our morphological nalyzer has done all the necessary work for the recognition and classi-fication of proper names, numerical and temporal expressions, i.e. Named Entity (NE) items in the Japanese text. The analyzer is called "Amorph". Amorph rec-ognizes NE items in two stages: dictionary lookup and rule application. First, it uses several kinds o