This report introduces the Attention Visualizer package, which is crafted to visually illustrate the significance of individual words in encoder-only transformer-based models. In contrast to other methods that center on tokens and self-attention scores, our approach will examine the words and their impact on the final embedding representation. Libraries like this play a crucial role in enhancing the interpretability and explainability of neural networks. They offer the opportunity to illuminate their internal mechanisms, providing a better understanding of how they operate and can be enhanced. You can access the code and review examples on the following GitHub repository: https://github.com/AlaFalaki/AttentionVisualizer.
@article{arxiv.2308.14850,
title = {Attention Visualizer Package: Revealing Word Importance for Deeper Insight into Encoder-Only Transformer Models},
author = {Ala Alam Falaki and Robin Gras},
journal= {arXiv preprint arXiv:2308.14850},
year = {2023}
}