High Quality Knowledge Graphs from recent English, French and German Emergent Trends with the example of COVID-19

以 COVID-19 为例的最新英语、法语和德语新兴趋势的高质量知识图

• 批准号: 490998901
• 负责人: Professor Dr. Sven Groppe
• 金额: --
• 依托单位: Institut für Informationssysteme (IFIS)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 资助国家: 德国
• 项目状态: 未结题
• 来源: https://gepris.dfg.de/gepris/projekt/490998901?language=en
• 关键词: Quality; Knowledge; Graphs; recent; English

The COVID-19 pandemic has stopped social and economical activities today. The total cost of the recent pandemic is estimated by 16 trillion USD by only considering the US and aggregating mortality, morbidity, mental health conditions, and direct economic losses on the assumption of the pandemic is substantially ending in fall of 2021. Hence an extensive analysis of the COVID-19 outbreak and the global responses are essential for preparing humanity for such future situations. Since the early 2020, hundreds of studies have been carried out to analyse, understand, track and model various aspects of the pandemic. Our project aims at providing the means for such kind of analysis, focusing for the first time at capturing inconsistencies/complementarities between these studies through (1) a general view of how facts about the pandemic evolve across time and languages, and (2) a high quality evaluation of these facts in enriched knowledge graphs to support further analysis. This is a highly collaborative project involving complementary expertise from natural language processing, databases and knowledge graph in order to generate high-quality knowledge graphs for emergent English, French and German trends with the example of COVID-19. The methodology and results of QualityOnt were designed to be generic enough to ensure their reusability in other future sanitary crises situations.

COVID-19大流行已停止了今天的社会和经济活动。仅考虑美国，并假设疫情将于二零二一年秋季基本结束，将死亡率、发病率、精神健康状况及直接经济损失合计，近期疫情的总成本估计为16万亿美元。因此，对COVID-19疫情的广泛分析和全球应对措施对于人类为未来的这种情况做好准备至关重要。自2020年初以来，已进行了数百项研究，以分析、了解、跟踪和模拟疫情的各个方面。我们的项目旨在为此类分析提供手段，首次侧重于通过以下方式捕捉这些研究之间的不一致性/互补性：（1）关于流行病的事实如何随时间和语言演变的一般视图，以及（2）在丰富的知识图中对这些事实进行高质量的评估，以支持进一步的分析。这是一个高度协作的项目，涉及自然语言处理、数据库和知识图谱的互补专业知识，以COVID-19为例，为英语、法语和德语的新兴趋势生成高质量的知识图谱。QualityOnt的方法和结果被设计为足够通用，以确保其在未来其他卫生危机情况下的可重复使用。