Ecole d'ingénieur et centre de recherche en Sciences du numérique

Towards a benchmark for fact checking with knowledge bases

Huynh, Viet Phi; Papotti, Paolo

RoD 2018, Reasoning on Data Workshop, collocated with WWW 2018, April 24, 2018, Lyon, France

Fact checking is the task of determining if a given claim holds. Several algorithms have been developed to check facts with reference information in the form of knowledge bases. While individual algorithms have been experimentally evaluated, we provide a first publicly available benchmark evaluating fact checking implementations across a range of assumptions about the properties of the facts and the reference data. We used our benchmark to compare algorithms designed on different principles and assumptions, as well as algorithms that can solve similar tasks developed in closely related communities. Our evaluation provided us with a number of new insights concerning the factors that impact the performance of the different methods.

Document Bibtex

Titre:Towards a benchmark for fact checking with knowledge bases
Département:Data Science
Eurecom ref:5468
Copyright: © 2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Bibtex: @inproceedings{EURECOM+5468, year = {2018}, title = {{T}owards a benchmark for fact checking with knowledge bases}, author = {{H}uynh, {V}iet {P}hi and {P}apotti, {P}aolo}, booktitle = {{R}o{D} 2018, {R}easoning on {D}ata {W}orkshop, collocated with {WWW} 2018, {A}pril 24, 2018, {L}yon, {F}rance}, address = {{L}yon, {FRANCE}}, month = {04}, url = {} }
Voir aussi: