Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction
This addresses the issue of long-tail entities with few supporting sentences in relation extraction, though it is an incremental improvement over existing distant supervision methods.
The paper tackles the problem of limited labeled data for relation extraction by introducing 2-hop distant supervision, which uses entity pairs from relational tables as anchors to gather more sentences for prediction. The result is that their method REDS2 outperforms baselines by a substantial margin on a benchmark dataset.
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.