The role of syntax in information extraction
Ralph Grishman · 1996
Our group at New York University has developed a number of information extraction systems over the past decade. In particular, we have been participants in the Message Understanding Conferences (MUCs) since MUC-1. During this time, while experimenting with many aspects of system design, we have retained a basic approach in which information extraction involves a phase of full syntactic analysis, followed by a semantic analysis of the syntactic structure [2]. Because we have a good, broad-coverage English grammar and a moderately effective method for recovering from parse failures, this approach held us in fairly good stead.