Team GESIS Cologne: An all in all sentence-based approach for FEVER

Wolfgang Otto


Abstract
In this system description of our pipeline to participate at the Fever Shared Task, we describe our sentence-based approach. Throughout all steps of our pipeline, we regarded single sentences as our processing unit. In our IR-Component, we searched in the set of all possible Wikipedia introduction sentences without limiting sentences to a fixed number of relevant documents. In the entailment module, we judged every sentence separately and combined the result of the classifier for the top 5 sentences with the help of an ensemble classifier to make a judgment whether the truth of a statement can be derived from the given claim.
Anthology ID:
W18-5524
Volume:
Proceedings of the First Workshop on Fact Extraction and VERification (FEVER)
Month:
November
Year:
2018
Address:
Brussels, Belgium
Venues:
EMNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
145–149
Language:
URL:
https://aclanthology.org/W18-5524
DOI:
10.18653/v1/W18-5524
Bibkey:
Cite (ACL):
Wolfgang Otto. 2018. Team GESIS Cologne: An all in all sentence-based approach for FEVER. In Proceedings of the First Workshop on Fact Extraction and VERification (FEVER), pages 145–149, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Team GESIS Cologne: An all in all sentence-based approach for FEVER (Otto, 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/W18-5524.pdf
Data
FEVER