Effective Attention Modeling for Neural Relation Extraction

TL;DR

This paper introduces a novel attention model for neural relation extraction that leverages syntactic information and multi-factor mechanisms to better capture long-distance interactions in sentences, improving performance on the NYT corpus.

Contribution

The paper proposes a new attention model that integrates syntactic info and multi-factor attention to enhance relation extraction, especially for long-distance and indirect relations.

Findings

Outperforms previous state-of-the-art models on NYT corpus

Effectively captures long-distance and indirect relations

Utilizes syntactic information to improve attention mechanisms

Abstract

Relation extraction is the task of determining the relation between two entities in a sentence. Distantly-supervised models are popular for this task. However, sentences can be long and two entities can be located far from each other in a sentence. The pieces of evidence supporting the presence of a relation between two entities may not be very direct, since the entities may be connected via some indirect links such as a third entity or via co-reference. Relation extraction in such scenarios becomes more challenging as we need to capture the long-distance interactions among the entities and other words in the sentence. Also, the words in a sentence do not contribute equally in identifying the relation between the two entities. To address this issue, we propose a novel and effective attention model which incorporates syntactic information of the sentence and a multi-factor attention mechanism. Experiments on the New York Times corpus show that our proposed model outperforms prior state-of-the-art models.