With the increased spread of the use of the internet, more and more people are searching about their health related problems on the web. However the number of sites with qualified and verified people answering their queries is quite low in comparison to the number of questions being put up. The rate of queries being searched on such sites has further increased due to the COVID-19 pandemic. On close inception it was found that the main reason people did not find solutions to their queries was that similar identification of questions on the medical domain was not done. Most of the queries people ask would have been answered, the only caveat being the question asked was different from the one asked by the particular user. In this research, we propose a Siamese-based BERT model to detect similar questions using a fine-tuning approach. The network is fine-tuned with medical question-answer pairs and then with question-question pairs to get a better question similarity prediction.
- Naveen Shenoy
- Alimurtaza Merchant
- Abhinav Bharali