Unsupervised Named-Entity Recognition: Generating Gazetteers and Resolving Ambiguity

by: David Nadeau, Peter Turney, Stan Matwin

Advances in Artificial Intelligence (2006), pp. 266-277.

View FullText article

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

sids, topher, AlisonBabeu, oktave-labs (group), brightbyte

Find related articles with these CiteULike tags

automatic-gazetteer-construction, disambiguation, gazetteers, named-entity-disambiguation, named-entity-recognition, ner, no-tag, web-page-wrappers

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).

@incollection{citeulike:1366689, 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).}, author = {Nadeau, David and Turney, Peter and Matwin, Stan }, citeulike-article-id = {1366689}, doi = {http://dx.doi.org/10.1007/11766247\_23}, journal = {Advances in Artificial Intelligence}, keywords = {disambiguation, gazetteers}, pages = {266--277}, posted-at = {2008-02-09 14:31:18}, priority = {2}, title = {Unsupervised Named-Entity Recognition: Generating Gazetteers and Resolving Ambiguity}, url = {http://dx.doi.org/10.1007/11766247\_23}, year = {2006} }

RIS record

TY - CHAP ID - citeulike:1366689 L3 - citeulike-article-id:1366689 TI - Unsupervised Named-Entity Recognition: Generating Gazetteers and Resolving Ambiguity JF - Advances in Artificial Intelligence SP - 266 EP - 277 N2 - 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). KW - disambiguation KW - gazetteers AU - Nadeau, David AU - Turney, Peter AU - Matwin, Stan PY - 2006/// UR - http://dx.doi.org/10.1007/11766247_23 ER -

RIS BibTeX