arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.09290cs.IRcs.CLcs.LG
收藏

提问可以概括语料库吗?使用问题生成来表征COVID-19研究

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

School of Electrical and Computing Engineering, UNICAMP(坎皮纳斯州立大学电气与计算机工程学院);NeuralMind Inteligência Artificial(NeuralMind 人工智能(公司));David R. Cheriton School of Computer Science, University of Waterloo(滑铁卢大学大卫·R·谢里顿计算机科学学院)

Gabriela Surita, Rodrigo Nogueira, Roberto Lotufo

摘要:

一些文本数据的潜在问题是什么?在这项工作中,我们研究使用问题生成模型来探索一系列文件。我们的方法被称为corpus 2 question,包括在语料库上应用预先训练的问题生成模型,并按频率和时间聚合生成的问题。这种技术是主题建模和词云等方法的替代方法,用于汇总大量文本数据。结果显示,将corpus 2 question应用于与COVID-19相关的科学文章语料库,可以生成与该主题相关的问题。最常见的问题是“什么是新冠肺炎”和“新冠肺炎的治疗方法是什么”。最常见的1000个问题包括“群体免疫的阈值是多少”和“ace 2在病毒进入中的作用是什么”。我们表明,所提出的方法产生了类似的问题,从CovidQA问答数据集的27个专家提出的问题中的13个。复制我们实验的代码和生成的问题可以在以下网站获得:https://github.com/unicamp-dl/corpus2question

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑