Abstract
This paper describes our system for SemEval-2019 Task 4: Hyperpartisan News Detection (Kiesel et al., 2019). We use pretrained BERT (Devlin et al., 2018) architecture and investigate the effect of different fine tuning regimes on the final classification task. We show that additional pretraining on news domain improves the performance on the Hyperpartisan News Detection task. Our system ranked 8th out of 42 teams with 78.3% accuracy on the held-out test dataset.- Anthology ID:
- S19-2175
- Volume:
- Proceedings of the 13th International Workshop on Semantic Evaluation
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota, USA
- Editors:
- Jonathan May, Ekaterina Shutova, Aurelie Herbelot, Xiaodan Zhu, Marianna Apidianaki, Saif M. Mohammad
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1007–1011
- Language:
- URL:
- https://aclanthology.org/S19-2175
- DOI:
- 10.18653/v1/S19-2175
- Cite (ACL):
- Osman Mutlu, Ozan Arkan Can, and Erenay Dayanik. 2019. Team Howard Beale at SemEval-2019 Task 4: Hyperpartisan News Detection with BERT. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 1007–1011, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
- Cite (Informal):
- Team Howard Beale at SemEval-2019 Task 4: Hyperpartisan News Detection with BERT (Mutlu et al., SemEval 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/S19-2175.pdf