# Rethinking Self-Attention: Towards Interpretability in Neural Parsing

arXiv: https://arxiv.org/abs/1911.03875 · HTML: https://mlsanity.com/paper/1911.03875/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2019.

## Built on by (most cited first, 3 of 3)

- [zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation](https://mlsanity.com/paper/2410.20808/) (2024)
- [Linguistically-Informed Neural Architectures for Lexical, Syntactic and Semantic Tasks in Sanskrit](https://mlsanity.com/paper/2308.08807/) (2023)
- [Fine-tuning of Large Language Models for Constituency Parsing Using a Sequence to Sequence Approach](https://mlsanity.com/paper/2510.16604/) (2025)

## Abstract (arXiv)

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.