Quan Xinyue, Xie Xiang, Liu Yang
Beijing Institute of Technology, Beijijng, China.
Front Artif Intell. 2024 Jan 5;6:1104064. doi: 10.3389/frai.2023.1104064. eCollection 2023.
With the rapid development of deep learning techniques, the applications have become increasingly widespread in various domains. However, traditional deep learning methods are often referred to as "black box" models with low interpretability of their results, posing challenges for their application in certain critical domains. In this study, we propose a comprehensive method for the interpretability analysis of sentiment models. The proposed method encompasses two main aspects: attention-based analysis and external knowledge integration. First, we train the model within sentiment classification and generation tasks to capture attention scores from multiple perspectives. This multi-angle approach reduces bias and provides a more comprehensive understanding of the underlying sentiment. Second, we incorporate an external knowledge base to improve evidence extraction. By leveraging character scores, we retrieve complete sentiment evidence phrases, addressing the challenge of incomplete evidence extraction in Chinese texts. Experimental results on a sentiment interpretability evaluation dataset demonstrate the effectiveness of our method. We observe a notable increase in accuracy by 1.3%, Macro-F1 by 13%, and MAP by 23%. Overall, our approach offers a robust solution for enhancing the interpretability of sentiment models by combining attention-based analysis and the integration of external knowledge.
随着深度学习技术的快速发展，其应用在各个领域日益广泛。然而，传统的深度学习方法通常被称为“黑箱”模型，其结果的可解释性较低，这给它们在某些关键领域的应用带来了挑战。在本研究中，我们提出了一种用于情感模型可解释性分析的综合方法。所提出的方法包括两个主要方面：基于注意力的分析和外部知识整合。首先，我们在情感分类和生成任务中训练模型，以从多个角度捕捉注意力分数。这种多角度方法减少了偏差，并提供了对潜在情感更全面的理解。其次，我们纳入外部知识库以改进证据提取。通过利用特征分数，我们检索完整的情感证据短语，解决了中文文本中证据提取不完整的挑战。在情感可解释性评估数据集上的实验结果证明了我们方法的有效性。我们观察到准确率显著提高了1.3%，宏F1提高了13%，平均精度均值提高了23%。总体而言，我们的方法通过结合基于注意力的分析和外部知识整合，为增强情感模型的可解释性提供了一个强大的解决方案。
