陈俊帆
点赞：
陈俊帆
点赞：
论文
E-VarM: Enhanced Variational Word Masks to Improve the Interpretability of Text Classification Models
发布时间：2025-10-22点击次数：
发表刊物：
Proceedings of the 29th International Conference on Computational Linguistics (COLING), CCF-B
摘要：
Enhancing the interpretability of text classification models can help increase the reliability of these models in real-world applications. Currently, most researchers focus on extracting task-specific words from inputs to improve the interpretability of the model. The competitive approaches exploit the Variational Information Bottleneck (VIB) to improve the performance of word masking at the word embedding layer to obtain task-specific words. However, these approaches ignore the multi-level semantics of the text, which can impair the interpretability of the model, and do not consider the risk of representation overlap caused by the VIB, which can impair the classification performance. In this paper, we propose an enhanced variational word masks approach, named E-VarM, to solve these two issues effectively. The E-VarM combines multi-level semantics from all hidden layers of the model to mask out task-irrelevant words and uses contrastive learning to readjust the distances between representations. Empirical studies on ten benchmark text classification datasets demonstrate that our approach outperforms the SOTA methods in simultaneously improving the interpretability and accuracy of the model.
合写作者：
Ling Ge,胡春明, Guanghui Ma, Junshuang Wu,陈俊帆, Jihong Liu, Hong Zhang, Wenyi Qin,张日崇
论文类型：
国际学术会议
页面范围：
1036-1050
是否译文：
否
发表时间：
2022-01-01