A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents
This addresses the limitation of sentence-level datasets in relation extraction by enabling cross-document analysis, though it is incremental as it builds on existing graph-based methods.
The paper tackles the problem of relation extraction across documents by proposing a cross-document approach where entities appear in different documents connected via chains, and it introduces a hierarchical entity graph convolutional network (HEGCN) that improves performance by 1.1% F1 score on a newly created two-hop dataset.
Distantly supervised datasets for relation extraction mostly focus on sentence-level extraction, and they cover very few relations. In this work, we propose cross-document relation extraction, where the two entities of a relation tuple appear in two different documents that are connected via a chain of common entities. Following this idea, we create a dataset for two-hop relation extraction, where each chain contains exactly two documents. Our proposed dataset covers a higher number of relations than the publicly available sentence-level datasets. We also propose a hierarchical entity graph convolutional network (HEGCN) model for this task that improves performance by 1.1\% F1 score on our two-hop relation extraction dataset, compared to some strong neural baselines.