Bootstrapping Distantly Supervised IE using Joint Learning and Small Well-structured Corpora

TL;DR

This paper introduces a novel framework for distantly-supervised relation extraction that leverages joint learning and small well-structured corpora to improve precision and recall in extracting relations.

Contribution

It proposes a joint learning approach combining concept and relation extraction, utilizing document structure and label propagation to enhance distantly-supervised relation extraction.

Findings

Significant improvement over state-of-the-art methods

Effective use of document structure for seed selection

Enhanced extraction accuracy through label propagation

Abstract

We propose a framework to improve performance of distantly-supervised relation extraction, by jointly learning to solve two related tasks: concept-instance extraction and relation extraction. We combine this with a novel use of document structure: in some small, well-structured corpora, sections can be identified that correspond to relation arguments, and distantly-labeled examples from such sections tend to have good precision. Using these as seeds we extract additional relation examples by applying label propagation on a graph composed of noisy examples extracted from a large unstructured testing corpus. Combined with the soft constraint that concept examples should have the same type as the second argument of the relation, we get significant improvements over several state-of-the-art approaches to distantly-supervised relation extraction.