Interpreting Randomly Wired Graph Models for Chinese NER

作     者：Jie Chen Jiabao Xu Xuefeng Xi Zhiming Cui Victor S.Sheng 

作者机构：The School of Electronic and Information EngineeringSuzhouUniversity of Science and TechnologySuzhouChina The School of Computer ScienceTexas Tech UniversityTexasUSA 

出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)

年 卷 期：2023年第134卷第1期

页      面：747-761页

核心收录：

学科分类：0710[理学-生物学] 07[理学] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 070101[理学-基础数学] 

基　　金：supported by the National Science Foundation of China(NSFC)underGrants 61876217 and 62176175 the Innovative Team of Jiangsu Province under Grant XYDXX-086 Jiangsu Postgraduate Research and Innovation Plan(KYCX20_2762) 

主　　题：Named entity recognition graph neural network saliency map random graph network interpretation 

摘      要：Interpreting deep neural networks is of great importance to understand and verify deep models for natural language processing(NLP)***,most existing approaches only focus on improving the performance of models but ignore their *** 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 ***,we develop a pipeline to explain the RWGNNby using Saliency Map and Adversarial *** results demonstrate that our approach can identify meaningful and reasonable interpretations for hidden states of RWGNN.