Similarity-based Memory Enhanced Joint Entity and Relation Extraction

TL;DR

This paper introduces a multi-task learning framework with bidirectional memory dependencies for document-level joint entity and relation extraction, significantly improving accuracy over existing methods.

Contribution

It proposes a novel multi-task learning approach with memory-like dependencies between tasks, enhancing joint extraction performance.

Findings

Outperforms existing methods on BioCreative V CDR corpus

Achieves state-of-the-art results in joint entity and relation extraction

Demonstrates the effectiveness of bidirectional memory dependencies

Abstract

Document-level joint entity and relation extraction is a challenging information extraction problem that requires a unified approach where a single neural network performs four sub-tasks: mention detection, coreference resolution, entity classification, and relation extraction. Existing methods often utilize a sequential multi-task learning approach, in which the arbitral decomposition causes the current task to depend only on the previous one, missing the possible existence of the more complex relationships between them. In this paper, we present a multi-task learning framework with bidirectional memory-like dependency between tasks to address those drawbacks and perform the joint problem more accurately. Our empirical studies show that the proposed approach outperforms the existing methods and achieves state-of-the-art results on the BioCreative V CDR corpus.