English

Knowledge-Aware Neural Networks for Medical Forum Question Classification

Computation and Language 2021-09-28 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2109.13141,
  title  = {Knowledge-Aware Neural Networks for Medical Forum Question Classification},
  author = {Soumyadeep Roy and Sudip Chakraborty and Aishik Mandal and Gunjan Balde and Prakhar Sharma and Anandhavelu Natarajan and Megha Khosla and Shamik Sural and Niloy Ganguly},
  journal= {arXiv preprint arXiv:2109.13141},
  year   = {2021}
}

Comments

5 pages, accepted as a short paper to CIKM 2021

R2 v1 2026-06-24T06:23:20.894Z