2003 NamedEntityRecognitionwithChara

From GM-RKB
(Redirected from Klein et al. 2003)
Jump to navigation Jump to search

Subject Headings: Supervised NER Algorithm, Text Item Predictor Feature, Word-Internal Substring Feature, Character n-Gram Feature.

Notes

Cited By

Quotes

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 [math]\displaystyle{ F_1 }[/math] 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.

References

;

 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2003 NamedEntityRecognitionwithCharaDan Klein
Christopher D. Manning
Huy Nguyen
Joseph Smarr
Named Entity Recognition with Character-level Models10.3115/1119176.1119204