2 papers
cs.CL2024
Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis
Zhenxiao Cheng, Jie Zhou, Wen Wu +2
Gradient-based explanation methods are increasingly used to interpret neural models in natural language processing (NLP) due to their high fidelity. Such methods determine word-lev…
cs.CL2023
Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment Classification via Small Explanation Annotations
Zhenxiao Cheng, Jie Zhou, Wen Wu +2
Gradient-based explanation methods play an important role in the field of interpreting complex deep neural networks for NLP models. However, the existing work has shown that the gr…