A Fact Checking and Verification System for FEVEROUS Using a Zero-Shot Learning Approach
Orkun Temiz, Özgün Ozan Kılıç, Arif Ozan Kızıldağ, Tuğba Taşkaya Temizel
Abstract
In this paper, we propose a novel fact checking and verification system to check claims against Wikipedia content. Our system retrieves relevant Wikipedia pages using Anserini, uses BERT-large-cased question answering model to select correct evidence, and verifies claims using XLNET natural language inference model by comparing it with the evidence. Table cell evidence is obtained through looking for entity-matching cell values and TAPAS table question answering model. The pipeline utilizes zero-shot capabilities of existing models and all the models used in the pipeline requires no additional training. Our system got a FEVEROUS score of 0.06 and a label accuracy of 0.39 in FEVEROUS challenge.- Anthology ID:
- 2021.fever-1.13
- Volume:
- Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER)
- Month:
- November
- Year:
- 2021
- Address:
- Dominican Republic
- Venue:
- FEVER
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 113–120
- Language:
- URL:
- https://aclanthology.org/2021.fever-1.13
- DOI:
- 10.18653/v1/2021.fever-1.13
- Cite (ACL):
- Orkun Temiz, Özgün Ozan Kılıç, Arif Ozan Kızıldağ, and Tuğba Taşkaya Temizel. 2021. A Fact Checking and Verification System for FEVEROUS Using a Zero-Shot Learning Approach. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), pages 113–120, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- A Fact Checking and Verification System for FEVEROUS Using a Zero-Shot Learning Approach (Temiz et al., FEVER 2021)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2021.fever-1.13.pdf
- Data
- FEVER, FEVEROUS