Rethinking Self-Attention: Towards Interpretability in Neural Parsing

TL;DR

This paper introduces the Label Attention Layer, a novel self-attention mechanism that enhances interpretability in neural parsing by representing labels directly, achieving state-of-the-art results with fewer layers.

Contribution

The paper proposes the Label Attention Layer, integrating label-specific attention into self-attention for improved interpretability and efficiency in neural parsing models.

Findings

Achieved new state-of-the-art results on PTB and Chinese Treebank.

Required fewer self-attention layers than previous models.

Learned relations between syntactic categories through attention heads.

Abstract

Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent work has shown that model representations can benefit from label-specific information, while facilitating interpretation of predictions. We introduce the Label Attention Layer: a new form of self-attention where attention heads represent labels. We test our novel layer by running constituency and dependency parsing experiments and show our new model obtains new state-of-the-art results for both tasks on both the Penn Treebank (PTB) and Chinese Treebank. Additionally, our model requires fewer self-attention layers compared to existing work. Finally, we find that the Label Attention heads learn relations between syntactic categories and show pathways to analyze errors.