Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion

TL;DR

Eider is a framework for document-level relation extraction that efficiently extracts evidence and fuses information during inference, improving accuracy while reducing computational costs.

Contribution

It introduces a joint training approach for evidence extraction and relation extraction, along with an inference method that combines evidence-based and full-document predictions.

Findings

Outperforms state-of-the-art on three benchmarks

Improves F1 scores by over 1 point

Efficient in memory and runtime

Abstract

Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document. Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the evidence, are often sufficient for humans to predict the relation of an entity pair. In this paper, we propose an evidence-enhanced framework, Eider, that empowers DocRE by efficiently extracting evidence and effectively fusing the extracted evidence in inference. We first jointly train an RE model with a lightweight evidence extraction model, which is efficient in both memory and runtime. Empirically, even training the evidence model on silver labels constructed by our heuristic rules can lead to better RE performance. We further design a simple yet effective inference process that makes RE predictions on both extracted evidence and the full document, then fuses the predictions through a blending layer. This allows Eider to focus on important sentences while still having access to the complete information in the document. Extensive experiments show that Eider outperforms state-of-the-art methods on three benchmark datasets (e.g., by 1.37/1.26 Ign F1/F1 on DocRED).