2002 · 369 citations · 17 references
ComputingComputer ScienceComputational LinguisticsNatural Language ProcessingSemanticsConcept ExtractionInformation ExtractionLanguage ModelingLexical SemanticsSemantic AnnotationAutomatic Lexicon ConstructionPattern ExtractionPrecisionWord Classification
This paper describes a bootstrapping algorithm called Basilisk that learns high-quality semantic lexicons for multiple categories. Basilisk begins with an unannotated corpus and seed words for each semantic category, which are then bootstrapped to learn new words for each category. Basilisk hypothesizes the semantic class of a word based on collective information over a large body of extraction pattern contexts. We evaluate Basilisk on six semantic categories. The semantic lexicons produced by Basilisk have higher precision than those produced by previous techniques, with several categories showing substantial improvement.
17
Automatic acquisition of hyponyms from large text corpora
Marti A. Hearst · 1992 · 3.3K citations · Full text
Unsupervised Models for Named Entity Classification
Michael Collins, Yoram Singer · 1999 · 817 citations