论文标题
问题可以总结语料库吗？使用问题生成来表征COVID-19
Can questions summarize a corpus? Using question generation for characterizing COVID-19 research
论文作者
论文摘要
关于某些文本数据的潜在问题是什么？在这项工作中，我们使用问题生成模型进行调查以探索文档集合。我们的方法称为Colpus2问题，包括在语料库上应用预训练的问题生成模型，并按频率和时间汇总结果问题。此技术是诸如主题建模和单词云之类的方法的替代方法，用于汇总大量文本数据。结果表明，将colpus2 question应用于与Covid-19有关的科学文章的语料库产生有关该主题的相关问题。最常见的问题是“什么是Covid 19”和“ Covid的治疗方法”。在1000个最常见的问题中，有“什么是牛群免疫的门槛”和“ ACE2在病毒进入中的作用是什么”。我们表明，该提出的方法为Covidqa问题回答数据集的27个专家问题中的13个中的13个产生了类似的问题。 重现我们的实验和生成问题的代码可在以下网址提供：https：//github.com/unicamp-dl/corpus2question
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
