Joint Distant and Direct Supervision for Relation Extraction

Supervised approaches to Relation Extraction (RE) are characterized by higher accuracy than unsupervised models. Unfortunately, their applicability is limited by the need of training data for each relation type. Automatic creation of such data using Distant Supervision (DS) provides a promising solution to the problem. In this paper, we study DS for designing endto-end systems of sentence-level RE. In particular, we propose a joint model between Web data derived with DS and manually annotated data from ACE. The results show (i) an improvement on the previous state-of-the-art in ACE, which provides important evidence of the benefit of DS; and (ii) a rather good accuracy on extracting 52 types of relations from Web data, which suggests the applicability of DS for general RE.