A Robust Risk Minimization based Named Entity Recognition System

Tong Zhang; David Johnson

doi:10.3115/1119176.1119210

A Robust Risk Minimization based Named Entity Recognition System

Tong Zhang, David Johnson

Research output: Contribution to conference › Conference Paper › peer-review

54 Citations (Scopus)

Abstract

This paper describes a robust linear classification system for Named Entity Recognition. A similar system has been applied to the CoNLL text chunking shared task with state of the art performance. By using different linguistic features, we can easily adapt this system to other token-based linguistic tagging problems. The main focus of the current paper is to investigate the impact of various local linguistic features for named entity recognition on the CoNLL-2003 (Tjong Kim Sang and De Meulder, 2003) shared task data. We show that the system performance can be enhanced significantly with some relative simple token-based features that are available for many languages. Although more sophisticated linguistic features will also be helpful, they provide much less improvement than might be expected.

Original language	English
Pages	204-207
Number of pages	4
DOIs	https://doi.org/10.3115/1119176.1119210
Publication status	Published - 2003
Externally published	Yes
Event	7th Conference on Natural Language Learning, CoNLL 2003 at HLT-NAACL 2003 - Edmonton, Canada Duration: 31 May 2003 → 1 Jun 2003

Conference

Conference	7th Conference on Natural Language Learning, CoNLL 2003 at HLT-NAACL 2003
Country/Territory	Canada
City	Edmonton
Period	31/05/03 → 1/06/03

Bibliographical note

Publisher Copyright:
© 2003 Proceedings of the 7th Conference on Natural Language Learning, CoNLL 2003 at HLT-NAACL 2003. All rights reserved.

Access to Document

10.3115/1119176.1119210

Cite this

@conference{1dab5df88d474936a55d9198de0c8e12,

title = "A Robust Risk Minimization based Named Entity Recognition System",

abstract = "This paper describes a robust linear classification system for Named Entity Recognition. A similar system has been applied to the CoNLL text chunking shared task with state of the art performance. By using different linguistic features, we can easily adapt this system to other token-based linguistic tagging problems. The main focus of the current paper is to investigate the impact of various local linguistic features for named entity recognition on the CoNLL-2003 (Tjong Kim Sang and De Meulder, 2003) shared task data. We show that the system performance can be enhanced significantly with some relative simple token-based features that are available for many languages. Although more sophisticated linguistic features will also be helpful, they provide much less improvement than might be expected.",

author = "Tong Zhang and David Johnson",

note = "Publisher Copyright: {\textcopyright} 2003 Proceedings of the 7th Conference on Natural Language Learning, CoNLL 2003 at HLT-NAACL 2003. All rights reserved.; 7th Conference on Natural Language Learning, CoNLL 2003 at HLT-NAACL 2003 ; Conference date: 31-05-2003 Through 01-06-2003",

year = "2003",

doi = "10.3115/1119176.1119210",

language = "English",

pages = "204--207",

}

TY - CONF

T1 - A Robust Risk Minimization based Named Entity Recognition System

AU - Zhang, Tong

AU - Johnson, David

PY - 2003

Y1 - 2003

N2 - This paper describes a robust linear classification system for Named Entity Recognition. A similar system has been applied to the CoNLL text chunking shared task with state of the art performance. By using different linguistic features, we can easily adapt this system to other token-based linguistic tagging problems. The main focus of the current paper is to investigate the impact of various local linguistic features for named entity recognition on the CoNLL-2003 (Tjong Kim Sang and De Meulder, 2003) shared task data. We show that the system performance can be enhanced significantly with some relative simple token-based features that are available for many languages. Although more sophisticated linguistic features will also be helpful, they provide much less improvement than might be expected.

AB - This paper describes a robust linear classification system for Named Entity Recognition. A similar system has been applied to the CoNLL text chunking shared task with state of the art performance. By using different linguistic features, we can easily adapt this system to other token-based linguistic tagging problems. The main focus of the current paper is to investigate the impact of various local linguistic features for named entity recognition on the CoNLL-2003 (Tjong Kim Sang and De Meulder, 2003) shared task data. We show that the system performance can be enhanced significantly with some relative simple token-based features that are available for many languages. Although more sophisticated linguistic features will also be helpful, they provide much less improvement than might be expected.

UR - https://openalex.org/W2087556608

UR - https://www.scopus.com/pages/publications/84919495233

U2 - 10.3115/1119176.1119210

DO - 10.3115/1119176.1119210

M3 - Conference Paper

SP - 204

EP - 207

T2 - 7th Conference on Natural Language Learning, CoNLL 2003 at HLT-NAACL 2003

Y2 - 31 May 2003 through 1 June 2003

ER -

A Robust Risk Minimization based Named Entity Recognition System

Abstract

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this