Rethinking Self-Attention: Towards Interpretability in Neural Parsing

2019/11/10 by Mrini, Khalil, Dernoncourt, Franck, Tran, Quan +3 · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.1911.03875

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.

Cited by

• Fine-tuning of Large Language Models for Constituency Parsing Using a Sequence to Sequence Approach

Related

• Is Attention Interpretable?
• Attention Interpretability Across NLP Tasks
• Attention is not Explanation
• Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding
• Why Attentions May Not Be Interpretable?