论文标题
科学检查器：提取性树牛的问题回答科学事实检查
Science Checker: Extractive-Boolean Question Answering For Scientific Fact Checking
论文作者
论文摘要
随着科学出版物的爆炸性增长，使科学知识和事实检查的综合成为越来越复杂的任务。在本文中，我们提出了一种多任务方法，用于根据研究文章中事实和证据的共同推理来验证科学问题。我们提出了（1）自动信息摘要的智能组合和（2）布尔值的回答，该问题允许仅从摘要后获得的摘录产生一个科学问题的答案。因此，在给定的主题上，我们提出的方法基于纸张摘要进行结构化的内容建模，以回答一个科学问题，同时突出了讨论该主题的论文中的文本。我们将最终系统基于端到端的提取问题回答（EQA）与三个输出分类模型相结合，以执行对问题的深入语义理解，以说明多个响应的汇总。借助我们的光线和快速提议的体系结构，我们达到了4％的平均错误率，而F1得分为95.6％。通过在欧洲PMC的医疗和健康领域中，通过两种质量检查模型（BERT，ROBERTA）进行实验来支持我们的结果。
With the explosive growth of scientific publications, making the synthesis of scientific knowledge and fact checking becomes an increasingly complex task. In this paper, we propose a multi-task approach for verifying the scientific questions based on a joint reasoning from facts and evidence in research articles. We propose an intelligent combination of (1) an automatic information summarization and (2) a Boolean Question Answering which allows to generate an answer to a scientific question from only extracts obtained after summarization. Thus on a given topic, our proposed approach conducts structured content modeling based on paper abstracts to answer a scientific question while highlighting texts from paper that discuss the topic. We based our final system on an end-to-end Extractive Question Answering (EQA) combined with a three outputs classification model to perform in-depth semantic understanding of a question to illustrate the aggregation of multiple responses. With our light and fast proposed architecture, we achieved an average error rate of 4% and a F1-score of 95.6%. Our results are supported via experiments with two QA models (BERT, RoBERTa) over 3 Million Open Access (OA) articles in the medical and health domains on Europe PMC.
