Can questions summarize a corpus? Using question generation for characterizing COVID-19 research

TL;DR

This paper explores using question generation models to analyze and summarize large collections of COVID-19 research articles by generating and aggregating relevant questions, offering an alternative to traditional summarization methods.

Contribution

The authors introduce corpus2question, a novel method applying pre-trained question generation models to summarize textual data through question aggregation, demonstrating its effectiveness on COVID-19 literature.

Findings

Generated relevant questions about COVID-19 topics.

Most frequent questions include 'what is covid 19' and 'what is the treatment for covid'.

The method matched 13 of 27 expert questions from CovidQA.

Abstract

What are the latent questions on some textual data? In this work, we investigate using question generation models for exploring a collection of documents. Our method, dubbed corpus2question, consists of applying a pre-trained question generation model over a corpus and aggregating the resulting questions by frequency and time. This technique is an alternative to methods such as topic modelling and word cloud for summarizing large amounts of textual data. Results show that applying corpus2question on a corpus of scientific articles related to COVID-19 yields relevant questions about the topic. The most frequent questions are "what is covid 19" and "what is the treatment for covid". Among the 1000 most frequent questions are "what is the threshold for herd immunity" and "what is the role of ace2 in viral entry". We show that the proposed method generated similar questions for 13 of the 27 expert-made questions from the CovidQA question answering dataset. The code to reproduce our experiments and the generated questions are available at: https://github.com/unicamp-dl/corpus2question