Yanming Ye


pdf bib
Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verification
Zhiwei Zhang | Jiyi Li | Fumiyo Fukumoto | Yanming Ye
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Scientific claim verification can help the researchers to easily find the target scientific papers with the sentence evidence from a large corpus for the given claim. Some existing works propose pipeline models on the three tasks of abstract retrieval, rationale selection and stance prediction. Such works have the problems of error propagation among the modules in the pipeline and lack of sharing valuable information among modules. We thus propose an approach, named as ARSJoint, that jointly learns the modules for the three tasks with a machine reading comprehension framework by including claim information. In addition, we enhance the information exchanges and constraints among tasks by proposing a regularization term between the sentence attention scores of abstract retrieval and the estimated outputs of rational selection. The experimental results on the benchmark dataset SciFact show that our approach outperforms the existing works.


pdf bib
HSCNN: A Hybrid-Siamese Convolutional Neural Network for Extremely Imbalanced Multi-label Text Classification
Wenshuo Yang | Jiyi Li | Fumiyo Fukumoto | Yanming Ye
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

The data imbalance problem is a crucial issue for the multi-label text classification. Some existing works tackle it by proposing imbalanced loss objectives instead of the vanilla cross-entropy loss, but their performances remain limited in the cases of extremely imbalanced data. We propose a hybrid solution which adapts general networks for the head categories, and few-shot techniques for the tail categories. We propose a Hybrid-Siamese Convolutional Neural Network (HSCNN) with additional technical attributes, i.e., a multi-task architecture based on Single and Siamese networks; a category-specific similarity in the Siamese structure; a specific sampling method for training HSCNN. The results using two benchmark datasets and three loss objectives show that our method can improve the performance of Single networks with diverse loss objectives on the tail or entire categories.