Paper: An Effective Two-Stage Model For Exploiting Non-Local Dependencies In Named Entity Recognition

ACL ID P06-1141
Title An Effective Two-Stage Model For Exploiting Non-Local Dependencies In Named Entity Recognition
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006
Authors

This paper shows that a simple two-stage approach to handle non-local dependen- cies in Named Entity Recognition (NER) can outperform existing approaches that handle non-local dependencies, while be- ing much more computationally efficient. NER systems typically use sequence mod- els for tractable inference, but this makes them unable to capture the long distance structure present in text. We use a Con- ditional Random Field (CRF) based NER system using local features to make pre- dictions and then train another CRF which uses both local information and features extracted from the output of the first CRF. Using features capturing non-local depen- dencies from the same document, our ap- proach yields a 12.6% relative error re- duction on the F1 score, over state-of-the- art NER systems usin...