Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction

TL;DR

This paper introduces 2-hop distant supervision for relation extraction, leveraging relational tables and anchor entity pairs to improve accuracy, especially for long-tail entities, using a hierarchical neural model called REDS2.

Contribution

It proposes a novel 2-hop DS strategy and a hierarchical neural model REDS2 that effectively combines 1-hop and 2-hop supervision signals for relation extraction.

Findings

REDS2 outperforms baselines on benchmark datasets.

2-hop DS improves relation extraction for long-tail entities.

Hierarchical fusion enhances information utilization.

Abstract

Distant supervision (DS) has been widely used to automatically construct (noisy) labeled data for relation extraction (RE). Given two entities, distant supervision exploits sentences that directly mention them for predicting their semantic relation. We refer to this strategy as 1-hop DS, which unfortunately may not work well for long-tail entities with few supporting sentences. In this paper, we introduce a new strategy named 2-hop DS to enhance distantly supervised RE, based on the observation that there exist a large number of relational tables on the Web which contain entity pairs that share common relations. We refer to such entity pairs as anchors for each other, and collect all sentences that mention the anchor entity pairs of a given target entity pair to help relation prediction. We develop a new neural RE method REDS2 in the multi-instance learning paradigm, which adopts a hierarchical model structure to fuse information respectively from 1-hop DS and 2-hop DS. Extensive experimental results on a benchmark dataset show that REDS2 can consistently outperform various baselines across different settings by a substantial margin.