Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision

TL;DR

This paper introduces a hierarchical relation-guided model that leverages entity types and sentence alignment to improve long-tail relation extraction in distant supervision, achieving state-of-the-art results.

Contribution

The work proposes a novel model that fully utilizes entity types and hierarchical alignment to enhance relation extraction, especially for long-tail relations, under distant supervision.

Findings

Achieves new state-of-the-art performance on benchmarks.

Effectively alleviates wrong labeling in distant supervision.

Improves long-tail relation extraction accuracy.

Abstract

Distant supervision uses triple facts in knowledge graphs to label a corpus for relation extraction, leading to wrong labeling and long-tail problems. Some works use the hierarchy of relations for knowledge transfer to long-tail relations. However, a coarse-grained relation often implies only an attribute (e.g., domain or topic) of the distant fact, making it hard to discriminate relations based solely on sentence semantics. One solution is resorting to entity types, but open questions remain about how to fully leverage the information of entity types and how to align multi-granular entity types with sentences. In this work, we propose a novel model to enrich distantly-supervised sentences with entity types. It consists of (1) a pairwise type-enriched sentence encoding module injecting both context-free and -related backgrounds to alleviate sentence-level wrong labeling, and (2) a hierarchical type-sentence alignment module enriching a sentence with the triple fact's basic attributes to support long-tail relations. Our model achieves new state-of-the-art results in overall and long-tail performance on benchmarks.