论文标题
解释经过文本数据培训的卷积网络
Interpreting convolutional networks trained on textual data
论文作者
论文摘要
由于深度学习的出现，在人工智能领域取得了许多进步。在几乎所有子场中，人工神经网络都达到或超过了人类水平的表现。但是，大多数模型是不可解释的。结果，很难相信他们的决定，尤其是在生与死的情况下。近年来，人们一直在创造可解释的人工智能的运动，但是迄今为止，大多数工作都集中在图像处理模型上，因为人类更容易感知视觉模式。在自然语言处理等其他领域的工作很少。在本文中，我们在文本数据上训练卷积模型，并通过研究其过滤器值来分析模型的全局逻辑。最后，我们在语料库中找到了模型逻辑中最重要的单词，然后删除其余的（95％）。仅在5％最重要的单词上接受培训的新模型可以实现与原始模型相同的性能，同时将训练时间减少一半以上。诸如此类的方法将有助于我们了解NLP模型，根据他们的单词选择来解释他们的决定，并通过寻找盲点和偏见来改善它们。
There have been many advances in the artificial intelligence field due to the emergence of deep learning. In almost all sub-fields, artificial neural networks have reached or exceeded human-level performance. However, most of the models are not interpretable. As a result, it is hard to trust their decisions, especially in life and death scenarios. In recent years, there has been a movement toward creating explainable artificial intelligence, but most work to date has concentrated on image processing models, as it is easier for humans to perceive visual patterns. There has been little work in other fields like natural language processing. In this paper, we train a convolutional model on textual data and analyze the global logic of the model by studying its filter values. In the end, we find the most important words in our corpus to our models logic and remove the rest (95%). New models trained on just the 5% most important words can achieve the same performance as the original model while reducing training time by more than half. Approaches such as this will help us to understand NLP models, explain their decisions according to their word choices, and improve them by finding blind spots and biases.
