Ontological Smoothing for Relation Extraction with Minimal Supervision

Abstract

Relation extraction, the process of converting natural language text into structured knowledge, is increasingly important. Most successful techniques use supervised machine learning to generate extractors from sentences that have been manually labeled with the relations' arguments. Unfortunately, these methods require numerous training examples, which are expensive and time-consuming to produce. This paper presents ontological smoothing, a semi-supervised technique that learns extractors for a set of minimally-labeled relations. Ontological smoothing has three phases. First, it generates a mapping between the target relations and a background knowledge-base. Second, it uses distant supervision to heuristically generate new training examples for the target relations. Finally, it learns an extractor from a combination of the original and newly-generated examples. Experiments on 65 relations across three target domains show that ontological smoothing can dramatically improve precision and recall, even rivaling fully supervised performance in many cases.