Team DOMLIN: Exploiting Evidence Enhancement for the FEVER Shared Task

Dominik Stammbach, Günter Neumann

In: Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER). Workshop on Fact Extraction and Verification (FEVER-2019) befindet sich EMNLP-IJCNLP 2019 November 3 Hong Kong China Seiten 105-109 Association for Computational Linguistics 11/2019.


This paper contains our system description for the second Fact Extraction and VERification (FEVER) challenge. We propose a two-staged sentence selection strategy to account for examples in the dataset where evidence is not only conditioned on the claim, but also on previously retrieved evidence. We use a publicly available document retrieval module and have fine-tuned BERT checkpoints for sentence selection and as the entailment classifier. We report a FEVER score of 68.46% on the blind testset.


Weitere Links

Second_FEVER_ShardTask_TEAM_DOMLIN_final_submission.pdf (pdf, 92 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence