Towards Large-scale Non-taxonomic Relation Extraction: Estimating the Precision of Rote Extractors
Enrique Alfonseca, María Ruiz-Casado, Manabu Okumura, Pablo Castells · 2006
In this paper, we describe a rote extractor that learns patterns for finding semantic relations in unrestricted text, with new procedures for pattern generalisation and scoring. An improved method for estimating the precision of the extracted patterns is presented. We show that our method approximates the precision values as evaluated by hand much better than the procedure traditionally used in rote extractors.