header

DeFacto - Temporal and Multilingual Deep Fact Validation

19 Pages Posted: 24 Jun 2018 First Look: Accepted

See all articles by Daniel Gerber

Daniel Gerber

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW)

Diego Esteve

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW)

Jens Lehmann

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW)

Lorenz Bühmann

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW)

Ricardo Usbeck

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW)

Axel-Cyrille Ngonga Ngomo

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW)

René Speck

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW)

Abstract

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

Keywords: Web of Data, Fact Validation, NLP, Provenance

Suggested Citation

Gerber, Daniel and Esteve, Diego and Lehmann, Jens and Bühmann, Lorenz and Usbeck, Ricardo and Ngonga Ngomo, Axel-Cyrille and Speck, René, DeFacto - Temporal and Multilingual Deep Fact Validation (2015). Journal of Web Semantics First Look. Available at SSRN: https://ssrn.com/abstract=3198925 or http://dx.doi.org/10.2139/ssrn.3198925

Daniel Gerber

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW) ( email )

Augustusplatz 10/11
Leipzig, 04109
Germany

Diego Esteve (Contact Author)

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW) ( email )

Augustusplatz 10/11
Leipzig, 04109
Germany

Jens Lehmann

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW) ( email )

Augustusplatz 10/11
Leipzig, 04109
Germany

Lorenz Bühmann

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW) ( email )

Augustusplatz 10/11
Leipzig, 04109
Germany

Ricardo Usbeck

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW) ( email )

Augustusplatz 10/11
Leipzig, 04109
Germany

Axel-Cyrille Ngonga Ngomo

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW) ( email )

Augustusplatz 10/11
Leipzig, 04109
Germany

René Speck

University of Leipzig - Agile Knowledge Engineering and Semantic Web (AKSW) ( email )

Augustusplatz 10/11
Leipzig, 04109
Germany

Register to save articles to
your library

Register

Paper statistics

Abstract Views
273
Downloads
4