资 源 简 介
Introduction
SRL (Simple rule language) is a regular expression based language developed to perform fact extraction from plain text. It is designed to operate as a two stage process by firstly extracting a set of predefined entity classes (named entity recognition) and then using these entities to fill in template slots using contextual rules. As an example, SRL is currently being used in the BioCaster project at the National Institute of Informatics for identifying disease outbreaks and their locations from news reports.
One of the key objectives of SRL has been to enable domain experts to develop their own lightweight text mining systems with minimal support from linguists and computer scientists. SRL uses a powerful yet easy-to-understand regular expression language designed specifically for handling tokenized text streams. SRL rules are often written using a simple combination of string literals and word classes (such as a list of country names) to define the
