Unsupervised Named-Entity Recognition: Generating Gazetteers and Resolving Ambiguity

Download	View accepted manuscript: Unsupervised Named-Entity Recognition: Generating Gazetteers and Resolving Ambiguity (PDF, 243 KiB)
Author	Search for: Nadeau, D.; Search for: Turney, Peter¹; Search for: Matwin, S.
Name affiliation	National Research Council of Canada. NRC Institute for Information Technology
Format	Text, Article
Conference	19th Canadian Conference on Artificial Intelligence, June 7, 2006, Québec City, Québec, Canada
Abstract	In this paper, we propose a named-entity recognition (NER) system that addresses two major limitations frequently discussed in the field. First, the system requires no human intervention such as manually labeling training data or creating gazetteers. Second, the system can handle more than the three classical named-entity types (person, location, and organization). We describe the system's architecture and compare its performance with a supervised system. We experimentally evaluate the system on a standard corpus, with the three classical named-entity types, and also on a new corpus, with a new named-entity type (car brands).
Publication date	2006
In	19th Canadian Conference on Artificial Intelligence [Proceedings].
Language	English
NRC number	NRCC 48727
NPARC number	5763522
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	82701912-a9a3-4e63-a9ad-69279a1c30a5
Record created	2009-03-29
Record modified	2020-10-09