Incorporating Global Contexts into Sentence Embedding for Relational Extraction at the Paragraph Level with Distant Supervision

Abstract

The increased demand for structured knowledge has created considerable interest in relation extraction (RE) from large collections of documents. In particular, distant supervision can be used for RE without manual annotation costs. Nevertheless, this paradigm only extracts relations from individual sentences that contain two target entities. This paper explores the incorporation of global contexts derived from paragraph-into-sentence embedding as a means of compensating for the shortage of training data in distantly supervised RE. Experiments on RE from Korean Wikipedia show that the presented approach can learn an exact RE from sentences (including grammatically incoherent sentences) without syntactic parsing.