Medical Literature Mining and Retrieval in a Conversational Setting
This addresses the need for accessible information retrieval tools for researchers and the public during the Covid-19 pandemic, but it is incremental as it combines existing methods in a new application.
The paper tackled the problem of processing and retrieving answers from the rapidly growing Covid-19 medical literature by developing a conversational system that uses a DialoGPT-based generation module and an ensemble retrieval module combining BM-25 and neural embeddings, achieving results through comparative experiments on retrieval methods.
The Covid-19 pandemic has caused a spur in the medical research literature. With new research advances in understanding the virus, there is a need for robust text mining tools which can process, extract and present answers from the literature in a concise and consumable way. With a DialoGPT based multi-turn conversation generation module, and BM-25 \& neural embeddings based ensemble information retrieval module, in this paper we present a conversational system, which can retrieve and answer coronavirus-related queries from the rich medical literature, and present it in a conversational setting with the user. We further perform experiments to compare neural embedding-based document retrieval and the traditional BM25 retrieval algorithm and report the results.