Document-level entity linking: CMCRC at TAC 2010

Will Radford; Ben Hachey; Joel Nothman; Matthew Honnibal; James R. Curran

Document-level entity linking: CMCRC at TAC 2010

Will Radford, Ben Hachey, Joel Nothman, Matthew Honnibal, James R. Curran

Centre for Language Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution

Abstract

This paper describes the CMCRC systems entered in the TAC 2010 entity linking challenge. The best performing system we describe implements the document-level entity linking system from Cucerzan (2007), with several additions that exploit global information. Our implementation of Cucerzan's method achieved a score of 74.9% in development experiments. Additional global information improves performance to 78.4%. On the TAC 2010 test data, our best system achieves a score of 84.4%, which is second in the overall rankings of submitted systems.

Original language	English
Title of host publication	Proceedings of the Text Analysis Conference
Publication status	Published - 2010
Event	Text Analysis Conference - Gaithersburg, United States Duration: 15 Nov 2010 → 16 Nov 2010

Conference

Conference	Text Analysis Conference
Country/Territory	United States
City	Gaithersburg
Period	15/11/10 → 16/11/10

Cite this

@inproceedings{d2bb8c685ba54695a298bfddc3b57e50,

title = "Document-level entity linking: CMCRC at TAC 2010",

abstract = "This paper describes the CMCRC systems entered in the TAC 2010 entity linking challenge. The best performing system we describe implements the document-level entity linking system from Cucerzan (2007), with several additions that exploit global information. Our implementation of Cucerzan's method achieved a score of 74.9% in development experiments. Additional global information improves performance to 78.4%. On the TAC 2010 test data, our best system achieves a score of 84.4%, which is second in the overall rankings of submitted systems.",

author = "Will Radford and Ben Hachey and Joel Nothman and Matthew Honnibal and Curran, {James R.}",

year = "2010",

language = "English",

booktitle = "Proceedings of the Text Analysis Conference",

note = "Text Analysis Conference ; Conference date: 15-11-2010 Through 16-11-2010",

}

TY - GEN

T1 - Document-level entity linking

T2 - Text Analysis Conference

AU - Radford, Will

AU - Hachey, Ben

AU - Nothman, Joel

AU - Honnibal, Matthew

AU - Curran, James R.

PY - 2010

Y1 - 2010

N2 - This paper describes the CMCRC systems entered in the TAC 2010 entity linking challenge. The best performing system we describe implements the document-level entity linking system from Cucerzan (2007), with several additions that exploit global information. Our implementation of Cucerzan's method achieved a score of 74.9% in development experiments. Additional global information improves performance to 78.4%. On the TAC 2010 test data, our best system achieves a score of 84.4%, which is second in the overall rankings of submitted systems.

AB - This paper describes the CMCRC systems entered in the TAC 2010 entity linking challenge. The best performing system we describe implements the document-level entity linking system from Cucerzan (2007), with several additions that exploit global information. Our implementation of Cucerzan's method achieved a score of 74.9% in development experiments. Additional global information improves performance to 78.4%. On the TAC 2010 test data, our best system achieves a score of 84.4%, which is second in the overall rankings of submitted systems.

M3 - Conference proceeding contribution

BT - Proceedings of the Text Analysis Conference

Y2 - 15 November 2010 through 16 November 2010

ER -

Document-level entity linking: CMCRC at TAC 2010

Abstract

Conference

Fingerprint

Cite this