Proceedings of the First Workshop on Fact Extraction and Verification

Team UMBC-FEVER: Claim verification using Semantic Lexical Resources

Ankur Padia, Francis Ferraro, and Tim Finin

November 1, 2018

We describe our system used in the 2018 FEVER shared task. The system employed a frame-based information retrieval approach to select Wikipedia sentences that provide evidence and a two-layer multilayer perceptron to classify a claim as correct or incorrect. Our submission achieved a score of 0.3966 on the Evidence F1 metric with an accuracy of 44.79% and a FEVER score of 0.2628 F1 points.

BibTeX OWL Tweet Scholar

Tags: ai, fact verification, fever, frames, knowledge graph, natural language processing, natural language processing, perceptron

Type: InProceedings

Publisher: Association for Computational Linguistics

Organization: ACL

Note: DOI: 10.18653/v1/W18-5527

Downloads: 1577 downloads