Knowledge-Aware Neural Networks for Medical Forum Question Classification
This addresses the need for efficient query routing in medical forums to handle high volumes with limited expert availability, though it is incremental as it builds on BERT with domain-specific enhancements.
The authors tackled the problem of automatically classifying medical queries in online forums to direct them to appropriate experts, achieving state-of-the-art performance on benchmark datasets and performing well in low-resource settings.
Online medical forums have become a predominant platform for answering health-related information needs of consumers. However, with a significant rise in the number of queries and the limited availability of experts, it is necessary to automatically classify medical queries based on a consumer's intention, so that these questions may be directed to the right set of medical experts. Here, we develop a novel medical knowledge-aware BERT-based model (MedBERT) that explicitly gives more weightage to medical concept-bearing words, and utilize domain-specific side information obtained from a popular medical knowledge base. We also contribute a multi-label dataset for the Medical Forum Question Classification (MFQC) task. MedBERT achieves state-of-the-art performance on two benchmark datasets and performs very well in low resource settings.