Named entity extraction based on a maximum entropy model and transformation rules

Abstract

This paper describes named entity (NE) extraction based on a maximum entropy (M.E.) model and transformation rules. There are two types of named entities when focusing on the relationship between morphemes and NEs as defined in the NE task of the IREX competition held in 1999. Each NE consists of one or more morphemes, or includes a substring of a morpheme. We extract the former type of NE by using the M.E. model. We then extract the latter type of NE by applying transformation rules to the text.