Yejin Cho


2023

pdf
Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy
Jiwoo Hong | Yejin Cho | Jiyoung Han | Jaemin Jung | James Thorne
Findings of the Association for Computational Linguistics: EMNLP 2023

We address an important gap in detecting political bias in news articles. Previous works that perform document classification can be influenced by the writing style of each news outlet, leading to overfitting and limited generalizability. Our approach overcomes this limitation by considering both the sentence-level semantics and the document-level rhetorical structure, resulting in a more robust and style-agnostic approach to detecting political bias in news articles. We introduce a novel multi-head hierarchical attention model that effectively encodes the structure of long documents through a diverse ensemble of attention heads. While journalism follows a formalized rhetorical structure, the writing style may vary by news outlet. We demonstrate that our method overcomes this domain dependency and outperforms previous approaches for robustness and accuracy. Further analysis and human evaluation demonstrate the ability of our model to capture common discourse structures in journalism.

2020

pdf
Leveraging WordNet Paths for Neural Hypernym Prediction
Yejin Cho | Juan Diego Rodriguez | Yifan Gao | Katrin Erk
Proceedings of the 28th International Conference on Computational Linguistics

We formulate the problem of hypernym prediction as a sequence generation task, where the sequences are taxonomy paths in WordNet. Our experiments with encoder-decoder models show that training to generate taxonomy paths can improve the performance of direct hypernym prediction. As a simple but powerful model, the hypo2path model achieves state-of-the-art performance, outperforming the best benchmark by 4.11 points in hit-at-one (H@1).