DeFacto - Temporal and Multilingual Deep Fact Validation

• DOI: 10.2139/ssrn.3198925
• Publication Date: 2018-07-11T15:31:20Z
• Authors: Daniel Gerber; Diego Esteve; Jens Lehmann; Lorenz BBhmann; Ricardo Usbeck; Axel-Cyrille Ngon...; Renn Speck
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

One of the main tasks when creating and maintaining knowledge bases is to validate facts provide sources for them in order ensure correctness traceability provided knowledge. So far, this task often addressed by human curators a three-step process: issuing appropriate keyword queries statement check using standard search engines, retrieving potentially relevant documents screening those content. The drawbacks process are manifold. Most importantly, it very time-consuming as experts have carry out several processes must read documents. In article, we present DeFacto (Deep Fact Validation) – an algorithm able finding trustworthy on Web. aims effective way validating supplying user with excerpts web pages well useful additional information including score confidence has input fact. To achieve goal, collects combines evidence from written languages. addition, provides support temporal scope, i.e., can estimate which time frame fact was valid. Given that automatic evaluation not been paid much attention so generic benchmarks evaluating these frameworks were previously available. We thus also framework checking make publicly