What is it about?
DDI relation extraction aims to extract drug interactions from existing literature data, in order to provide researchers with specific drug pair interaction relationships and also narrow the scope of drug trials. Existing work has taken network models as a review perspective. Through practical experiments, it has been found that the performance of DDI relation extraction models is more affected by additional feature information. Therefore, our work will provide a detailed introduction to existing DDI relation extraction works from an unprecedented perspective-feature supplementation.
Featured Image
Photo by freestocks on Unsplash
Why is it important?
Our work provides an overview of all deep learning based DDI relation extraction methods and summarizes all types of feature supplementation methods that have emerged. These feature supplementation methods have played different roles in different situations and are of great significance for other biomedical entity relation extraction problems, even for relation extraction problems in NLP.
Perspectives
Here you will find that the performance of the model is not only affected by different network structures.
Mingliang Dou
Taiyuan University of Technology
Read the Original
This page is a summary of: Drug-drug interaction relation extraction based on deep learning: A review, ACM Computing Surveys, February 2024, ACM (Association for Computing Machinery),
DOI: 10.1145/3645089.
You can read the full text:
Contributors
The following have contributed to this page
