Experiments on pattern-based relation learning

Abstract

Relation extraction is a sub-task of Information Extraction (IE) that is concerned with extracting semantic relations---such as antonymy, synonymy or hypernymy---between word pairs from corpus data. Past work in relation extraction has concentrated on creating a small set of patterns that are good indicators of whether a word pair contains a semantic relation. In recent years, there has been work on using machine learning to automatically learn these patterns from text. We build on this research in running a series of experiments to investigate the impact of corpus type, corpus size and different parameter settings on learning a range of lexical relations.