Global Relation Embedding for Relation Extraction

TL;DR

This paper introduces a global relation embedding method that leverages co-occurrence statistics to improve relation extraction accuracy under distant supervision, significantly reducing noise effects.

Contribution

It proposes a novel global statistics-based textual relation embedding approach that enhances existing models' performance in relation extraction tasks.

Findings

Improved relation extraction accuracy from 83.9% to 89.3%.

Embedding approach is more robust to training noise.

Significant performance gains on a popular dataset.

Abstract

We study the problem of textual relation embedding with distant supervision. To combat the wrong labeling problem of distant supervision, we propose to embed textual relations with global statistics of relations, i.e., the co-occurrence statistics of textual and knowledge base relations collected from the entire corpus. This approach turns out to be more robust to the training noise introduced by distant supervision. On a popular relation extraction dataset, we show that the learned textual relation embedding can be used to augment existing relation extraction models and significantly improve their performance. Most remarkably, for the top 1,000 relational facts discovered by the best existing model, the precision can be improved from 83.9% to 89.3%.