CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management

Abstract

The outbreak of COVID-19 raises attention from the researchers from various communities. While many scientific articles have been published, a system that can provide reliable information to COVID-19 related questions from the latest academic resources is crucial, especially for the medical community in the current time-critical race to treat patients and to find a cure for the virus. To address the requests, we propose our CAiRE-COVID, a neural-based system that uses open-domain question answering (QA) techniques combined with summarization techniques for mining the available scientific literature. It leverages the Information Retrieval (IR) system and QA models to extract relevant snippets from existing literature given a query. Fluent summaries are also provided to help understand the content in a more efficient way. Our system has been awarded as winner for one of the tasks in CORD-19 Kaggle Challenge. We also launched our CAiRE-COVID website for broader use. The code for our system is also open-sourced to bootstrap further study.