Publication: Team Howard Beale at SemEval-2019 task 4: hyperpartisan news detection with BERT
Files
Program
KU-Authors
KU Authors
Co-Authors
Dayanık, Erenay
Publication Date
Language
Embargo Status
NO
Journal Title
Journal ISSN
Volume Title
Alternative Title
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 system1 ranked 8th out of 42 teams with 78.3% accuracy on the held-out test dataset.
Source
Publisher
Association for Computational Linguistics (ACL)
Subject
Embedding, Named entity recognition, Entailment
Citation
Has Part
Source
Proceedings of the 13th Workshop on Semantic Evaluation
Book Series Title
Edition
DOI
10.18653/v1/S19-2175