Rethinking Self-Attention: Towards Interpretability in Neural Parsing
Autor: | Ndapa Nakashole, Quan Hung Tran, Franck Dernoncourt, Khalil Mrini, Walter Chang, Trung Bui |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Treebank 02 engineering and technology computer.software_genre Machine Learning (cs.LG) 03 medical and health sciences 0302 clinical medicine Dependency grammar 0202 electrical engineering electronic engineering information engineering Layer (object-oriented design) Interpretability Parsing Interpretation (logic) Computer Science - Computation and Language business.industry Self attention Syntax 030221 ophthalmology & optometry 020201 artificial intelligence & image processing Artificial intelligence business Computation and Language (cs.CL) computer Natural language processing |
Zdroj: | EMNLP (Findings) |
Popis: | 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. EMNLP 2020 |
Databáze: | OpenAIRE |
Externí odkaz: |