Medical Synonym Extraction with Concept Space Models
This addresses synonym extraction for healthcare applications, but it appears incremental as it builds on existing embedding methods with domain integration.
The paper tackles medical synonym extraction by integrating term embeddings with domain knowledge, achieving a large performance improvement over baselines on a dataset of over 1 million term pairs.
In this paper, we present a novel approach for medical synonym extraction. We aim to integrate the term embedding with the medical domain knowledge for healthcare applications. One advantage of our method is that it is very scalable. Experiments on a dataset with more than 1M term pairs show that the proposed approach outperforms the baseline approaches by a large margin.