How feasible is the reuse of grammars for Named Entity Recognition?

Proceedings of the Third International Conference on Language Resources and Evaluation (LREC 2002)

Abstract

In this paper, we argue that vital time is wasted in creating resources from scratch, instead of reusing existing grammars for NE recognition. We discuss three possible reasons for this and present our corresponding empirical results, that ground our argument and encourage more widespread use of valuable existing resources.