Automatic relation extraction among named entities from text contents

Abstract

The goal of our research is to reduce the manual effort and automate the process of relation extraction. To realize this intention, we investigate semi-supervised learning and unsupervised learning solutions to rival supervised learning methods so that we can resolve the problem of relation extraction with minimal human cost and still achieve comparable performance to supervised learning methods. First, we present a label propagation (LP) based semi-supervised learning algorithm for relation extraction problem to learn from both labeled and unlabeled data. Secondly, we introduce an unsupervised learning algorithm based on model order identification for automatic relation extraction. The model order identification is achieved by resampling-based stability analysis and used to infer the number of relation types between entity pairs automatically. Thirdly, we further investigate unsupervised learning solution for relation disambiguation using a spectral clustering strategy. The thesis evaluates the proposed methods using the ACE corpus.