Semi-supervised Semantic Pattern Discovery with Guidance from Unsupervised Pattern Clusters

Abstract

We present a simple algorithm for clustering semantic patterns based on distributional similarity and use cluster memberships to guide semi-supervised pattern discovery. We apply this approach to the task of relation extraction. The evaluation results demonstrate that our novel bootstrapping procedure significantly outperforms a standard bootstrapping. Most importantly, our algorithm can effectively prevent semantic drift and provide semi-supervised learning with a natural stopping criterion.