论文标题
在变压器中插入信息的瓶颈
Inserting Information Bottlenecks for Attribution in Transformers
论文作者
论文摘要
预处理的变形金刚在自然语言处理中跨任务实现了最新技术，激励研究人员研究其内部机制。一个普遍的方向是了解哪些特征对于预测很重要。在本文中，我们应用信息瓶颈来分析每个功能的归因以在黑框模型上进行预测。我们以伯特为例，并在定量和定性上评估我们的方法。我们在归因方面显示了我们方法的有效性，以及提供有关信息如何流过层的能力。我们证明，我们的技术在四个数据集上的降解测试中优于两种竞争方法。代码可在https://github.com/bazingagin/iba上找到。
Pretrained transformers achieve the state of the art across tasks in natural language processing, motivating researchers to investigate their inner mechanisms. One common direction is to understand what features are important for prediction. In this paper, we apply information bottlenecks to analyze the attribution of each feature for prediction on a black-box model. We use BERT as the example and evaluate our approach both quantitatively and qualitatively. We show the effectiveness of our method in terms of attribution and the ability to provide insight into how information flows through layers. We demonstrate that our technique outperforms two competitive methods in degradation tests on four datasets. Code is available at https://github.com/bazingagin/IBA.
