MC-DRE: Multi-Aspect Cross Integration for Drug Event/Entity Extraction

TL;DR

This paper introduces a multi-aspect cross-integration framework that enhances drug entity and event detection by capturing diverse contextual information, significantly outperforming existing methods on key tasks.

Contribution

It presents a novel multi-aspect cross-integration approach that combines semantic, syntactic, and medical contexts for improved drug-related information extraction.

Findings

Outperforms state-of-the-art on flat entity detection

Outperforms state-of-the-art on discontinuous event extraction

Effective multi-aspect contextual integration enhances detection accuracy

Abstract

Extracting meaningful drug-related information chunks, such as adverse drug events (ADE), is crucial for preventing morbidity and saving many lives. Most ADEs are reported via an unstructured conversation with the medical context, so applying a general entity recognition approach is not sufficient enough. In this paper, we propose a new multi-aspect cross-integration framework for drug entity/event detection by capturing and aligning different context/language/knowledge properties from drug-related documents. We first construct multi-aspect encoders to describe semantic, syntactic, and medical document contextual information by conducting those slot tagging tasks, main drug entity/event detection, part-of-speech tagging, and general medical named entity recognition. Then, each encoder conducts cross-integration with other contextual information in three ways: the key-value cross, attention cross, and feedforward cross, so the multi-encoders are integrated in depth. Our model outperforms all SOTA on two widely used tasks, flat entity detection and discontinuous event extraction.