Abstract

Neural networks are progressively assuming a larger role in individuals daily routines, as their complexity continues to grow. While the model demonstrates satisfactory performance when evaluated on the test data, it often yields unforeseen outcomes in real-world scenarios. To diagnose the source of these errors, understanding the decision-making process employed by the model becomes crucial. In this paper, we consider various methods of interpreting the BERT model in classification tasks, and also consider methods for evaluating interpretation methods using vector representations fastText, GloVe and Sentence-BERT.

中文翻译：

---

评估可解释性方法在文本分类任务中的性能

 抽象的

随着神经网络的复杂性不断增加，它们在个人日常生活中逐渐发挥着越来越大的作用。虽然该模型在测试数据评估时表现出令人满意的性能，但在现实场景中通常会产生不可预见的结果。为了诊断这些错误的根源，了解模型所采用的决策过程变得至关重要。在本文中，我们考虑了在分类任务中解释 BERT 模型的各种方法，还考虑了使用向量表示 fastText、GloVe 和 Sentence-BERT 评估解释方法的方法。