Team yeon-zi at semeval-2019 task 4: Hyperpartisan news detection by de-noising weakly-labeled data
Published in The 13th International Workshop on Semantic Evaluation, 2019
This paper describes our system submitted to SemEval-2019 Task 4: Hyperpartisan News Detection. We focus on removing the inherent noise in the hyperpartisanship dataset from both data-level and model-level by leveraging semi-supervised pseudo-labels and the state-of-the-art BERT model. Our model achieves 75.8% accuracy in the final by-article dataset without ensemble learning.
Recommended citation: Liu, Z., Lee, N., & Fung, P. (2019, June). Team yeon-zi at semeval-2019 task 4: Hyperpartisan news detection by de-noising weakly-labeled data. In Proceedings of the 13th International Workshop on Semantic Evaluation (pp. 1052-1056).