Jie Chen1, Jiabao Xu1, Xuefeng Xi1,*, Zhiming Cui1, Victor S. Sheng2
CMES-Computer Modeling in Engineering & Sciences, Vol.134, No.1, pp. 747-761, 2023, DOI:10.32604/cmes.2022.020771
Abstract Interpreting deep neural networks is of great importance to understand and verify deep models for natural language
processing (NLP) tasks. However, most existing approaches only focus on improving the performance of models
but ignore their interpretability. In this work, we propose a Randomly Wired Graph Neural Network (RWGNN)
by using graph to model the structure of Neural Network, which could solve two major problems (word-boundary
ambiguity and polysemy) of Chinese NER. Besides, we develop a pipeline to explain the RWGNN by using Saliency
Map and Adversarial Attacks. Experimental results demonstrate that our approach can identify meaningful and
reasonable interpretations for… More >
Login
Register
