MC-DRE: Multi-Aspect Cross Integration for Drug Event/Entity Extraction
This work addresses the extraction of adverse drug events from medical texts, which is crucial for preventing morbidity and saving lives, representing a domain-specific advancement.
The paper tackles the problem of extracting drug-related entities and events from unstructured medical conversations by proposing a multi-aspect cross-integration framework that captures semantic, syntactic, and contextual information. The model outperforms all state-of-the-art methods on flat entity detection and discontinuous event extraction tasks.
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.