论文信息 - - based Named Entity Disambiguation to Arbitrary Web Text

- based Named Entity Disambiguation to Arbitrary Web Text

This paper investigates the “named-entity disambiguation” task on the Web—identifying the referent of a string, found on an arbitrary Web page. The GROUNDER system, introduced in this paper, addresses two challenges not considered by previous work: how to utilize a priori information (e.g., Bill Clinton is more prominent on the Web than Clinton County) to improve disambiguation, and how to compose this prior information with contextual evidence. GROUNDER addresses both challenges by leveraging the user-contributed knowledge in Wikipedia and providing a novel formulation of the task. On a sample of strings drawn from the Web, GROUNDER achieves precision of 1.0 at recall 0.34, and precision 0.90 at recall 0.60.

S. Soderland | Anthony Fader

[1] O. William. Journal Of The American Statistical Association V-28 , 1932 .

[2] Editors , 2003 .

[3] Dan Roth,et al. Robust Reading: Identification and Tracing of Ambiguous Names , 2004, NAACL.

[4] P. Ivax,et al. A THEORY FOR RECORD LINKAGE , 2004 .

[5] Lise Getoor,et al. A Latent Dirichlet Model for Unsupervised Entity Resolution , 2005, SDM.

[6] Razvan C. Bunescu,et al. Using Encyclopedic Knowledge for Named entity Disambiguation , 2006, EACL.

[7] Silviu Cucerzan,et al. Large-Scale Named Entity Disambiguation Based on Wikipedia Data , 2007, EMNLP.

[8] Oren Etzioni,et al. Unsupervised Resolution of Objects and Relations on the Web , 2007, NAACL.

[9] Jordan B. Peterson. The Meaning of Meaning , 2007 .

[10] Oren Etzioni,et al. Open Information Extraction from the Web , 2007, CACM.