TY - CONF
T1 - MC-DRE: Multi-Aspect Cross Integration for Drug Event/Entity Extraction
AU - Yang, Jie
AU - Han, Soyeon caren
AU - Long, Siqu
AU - Poon, Josiah
AU - Nenadic, Goran
N1 - Publisher Copyright:
© 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.
PY - 2023/10/21
Y1 - 2023/10/21
N2 - 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.
AB - 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.
KW - cross-integration
KW - drug entity extraction
KW - medical entity recognition
UR - http://www.scopus.com/inward/record.url?scp=85178160194&partnerID=8YFLogxK
U2 - 10.1145/3583780.3615190
DO - 10.1145/3583780.3615190
M3 - Paper
SP - 4385
EP - 4389
ER -