Named entity recognition with character-level models

  • Authors:
  • Dan Klein;Joseph Smarr;Huy Nguyen;Christopher D. Manning

  • Affiliations:
  • Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA;Stanford University, Stanford, CA

  • Venue:
  • CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

We discuss two named-entity recognition models which use characters and character n-grams either exclusively or as an important part of their data representation. The first model is a character-level HMM with minimal context information, and the second model is a maximum-entropy conditional markov model with substantially richer context features. Our best model achieves an overall F1 of 86.07% on the English test data (92.31% on the development data). This number represents a 25% error reduction over the same model without word-internal (substring) features.