Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention

TL;DR

This paper introduces novel word attention models for distantly supervised relation extraction, proposes a new cleaner dataset, and demonstrates improved performance through extensive experiments.

Contribution

It presents two new word attention models, a combined model, and a new dataset that reduces noise for more credible evaluation.

Findings

The proposed models outperform existing methods.

The new dataset GDS reduces noise in test data.

Extensive experiments validate the effectiveness of the approaches.

Abstract

Relation extraction is the problem of classifying the relationship between two entities in a given sentence. Distant Supervision (DS) is a popular technique for developing relation extractors starting with limited supervision. We note that most of the sentences in the distant supervision relation extraction setting are very long and may benefit from word attention for better sentence representation. Our contributions in this paper are threefold. Firstly, we propose two novel word attention models for distantly- supervised relation extraction: (1) a Bi-directional Gated Recurrent Unit (Bi-GRU) based word attention model (BGWA), (2) an entity-centric attention model (EA), and (3) a combination model which combines multiple complementary models using weighted voting method for improved relation extraction. Secondly, we introduce GDS, a new distant supervision dataset for relation extraction. GDS removes test data noise present in all previous distant- supervision benchmark datasets, making credible automatic evaluation possible. Thirdly, through extensive experiments on multiple real-world datasets, we demonstrate the effectiveness of the proposed methods.