Distant Supervision for Relation Extraction with Hierarchical Attention-Based Networks

Abstract

Distant supervision employs external knowledge bases to automatically label corpora. The labeled sentences in a corpus are usually packaged and trained for relation extraction using a multi-instance learning paradigm. The automated distant supervision inevitably introduces label noises. Previous studies that used sentence-level attention mechanisms to de-noise neither considered correlation among sentences in a bag nor correlation among bags. This paper proposes hierarchical attention-based networks that can de-noise at both sentence and bag levels. In the calculation of bag representation, we provide weights to sentence representations using sentence-level attention that considers correlations among sentences in each bag. Then, we employ bag-level attention to merge the similar bags by considering their correlations and to provide properer weights in the calculation of bag group representation. Experimental results on the New York Times datasets show that the proposed method outperforms the state-of-the-art ones.

Tasks

Reproductions