COV19IR : COVID-19 Domain Literature Information Retrieval

TL;DR

This paper presents a transformer-based system for retrieving COVID-19 literature and answering related questions, addressing the challenge of managing the rapidly growing research corpus.

Contribution

It introduces two novel tasks—COVID-19 literature retrieval and question answering—and provides transformer-based solutions tailored for these tasks on the CORD-19 dataset.

Findings

Effective retrieval of COVID-19 literature demonstrated

Accurate COVID-19 question answering achieved

Solutions show promising results on CORD-19

Abstract

Increasing number of COVID-19 research literatures cause new challenges in effective literature screening and COVID-19 domain knowledge aware Information Retrieval. To tackle the challenges, we demonstrate two tasks along withsolutions, COVID-19 literature retrieval, and question answering. COVID-19 literature retrieval task screens matching COVID-19 literature documents for textual user query, and COVID-19 question answering task predicts proper text fragments from text corpus as the answer of specific COVID-19 related questions. Based on transformer neural network, we provided solutions to implement the tasks on CORD-19 dataset, we display some examples to show the effectiveness of our proposed solutions.