Improving English Named Entity Recognition

In recent years much of the work in named entity recognition has been focused on tackling entities in different languages or domains. However the task of English named entity recognition still remains to be solved. In this paper we explore more ways to improve the English named entity recognition system beyond just distributional semantics and the use of external gazetteer. These ways include pruning search space, increasing training data, chunked-based states, and active learning. Our experiments show we can still improve the English named entity recognition task and we find an improvement of at least .2% from our experiments.