Attention

This repo explores the relationship between attention in transformer models and the syntactic structure of human language.

Setup

Clone this repo
Install the requirements: pip install -r requirements.txt (you may want to do this in a virtual environment)
Install the required SpaCy model: python -m spacy download en_core_web_sm
Run the tests: pytest
Run the experiments: python -m attention

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
.vscode		.vscode
UD_Basque-BDT		UD_Basque-BDT
UD_Catalan-AnCora		UD_Catalan-AnCora
UD_English-GUM		UD_English-GUM
UD_French-Sequoia		UD_French-Sequoia
UD_Galician-CTG		UD_Galician-CTG
UD_Galician-TreeGal		UD_Galician-TreeGal
UD_Portuguese-CINTIL		UD_Portuguese-CINTIL
UD_Spanish-AnCora		UD_Spanish-AnCora
UD_Turkish-Penn		UD_Turkish-Penn
attention.egg-info		attention.egg-info
attention		attention
results_ca		results_ca
results_en		results_en
results_es		results_es
results_eu		results_eu
results_fr		results_fr
results_gl		results_gl
results_pt		results_pt
results_tr		results_tr
.gitignore		.gitignore
README.md		README.md
average_statistics_from_results.py		average_statistics_from_results.py
experiment_config.yaml		experiment_config.yaml
experiment_config_test.yaml		experiment_config_test.yaml
requirements.txt		requirements.txt
setup.py		setup.py