使用诊断分类解释用于基于情感的情感分类的神经注意力模型
Explaining a Neural Attention Model for Aspect-Based Sentiment Classification Using Diagnostic Classification
摘要：
许多用于基于情感的情感分类（ABSC）的高性能机器学习模型产生黑盒模型，因此几乎不能解释它们如何将特定情感值分类到某个方面。在本文中，我们提出了解释模型，检查的内部动态的一个国家的最先进的神经注意力模型，LCR-Rot-Hop，通过使用一种技术称为诊断分类。我们的诊断分类器是一个简单的神经网络，它评估LCR-Rot-hop模型的内部层是否编码了用于分类的有用单词信息，即，词性、情感值、体关系的存在以及词的体相关情感值。我们的结论是，在LCR-Rot-hop模型的低层编码的部分语音和情感值，而高层表示的方面和方面相关的情感值的话的关系的存在。
英文摘要：
Many high performance machine learning models for Aspect-Based Sentiment Classification (ABSC) produce black box models, and therefore barely explain how they classify a certain sentiment value towards an aspect. In this paper, we propose explanation models, that inspect the internal dynamics of a state-of-the-art neural attention model, the LCR-Rot-hop, by using a technique called Diagnostic Classification. Our diagnostic classifier is a simple neural network, which evaluates whether the internal layers of the LCR-Rot-hop model encode useful word information for classification, i.e., the part of speech, the sentiment value, the presence of aspect relation, and the aspect-related sentiment value of words. We conclude that the lower layers in the LCR-Rot-hop model encode the part of speech and the sentiment value, whereas the higher layers represent the presence of a relation with the aspect and the aspect-related sentiment value of words.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
