SEE: Syntax-aware Entity Embedding for Neural Relation Extraction

TL;DR

This paper introduces a syntax-aware entity embedding method for neural relation extraction that leverages dependency tree structures and attention mechanisms to improve relation classification accuracy.

Contribution

It proposes a novel syntax-aware entity embedding approach combining dependency tree encoding and attention, enhancing neural relation extraction performance.

Findings

Achieves state-of-the-art results on a real-world dataset.

Effectively utilizes all informative instances.

Improves relation classification accuracy.

Abstract

Distant supervised relation extraction is an efficient approach to scale relation extraction to very large corpora, and has been widely used to find novel relational facts from plain text. Recent studies on neural relation extraction have shown great progress on this task via modeling the sentences in low-dimensional spaces, but seldom considered syntax information to model the entities. In this paper, we propose to learn syntax-aware entity embedding for neural relation extraction. First, we encode the context of entities on a dependency tree as sentence-level entity embedding based on tree-GRU. Then, we utilize both intra-sentence and inter-sentence attentions to obtain sentence set-level entity embedding over all sentences containing the focus entity pair. Finally, we combine both sentence embedding and entity embedding for relation classification. We conduct experiments on a widely used real-world dataset and the experimental results show that our model can make full use of all informative instances and achieve state-of-the-art performance of relation extraction.