Code for "Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models" and "Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora"
30
stars
5
forks
source link
Please add dependencies to the repository and make a version #2
To make your code replicable, users would start from a virtual environment in Python and then run pip install -r requirements.txt to install all the packages needed for replication. To guarantee replicability, you'd need:
the requirements.txt, which you could generate by making a fresh virtual environment, installing all dependencies known to you (I saw torch there), and then run pip freeze > requirements.txt
make a version in GitHub, so we know to which version of your code the repository refers (e.g., if you develop it further)
To make your code replicable, users would start from a virtual environment in Python and then run
pip install -r requirements.txtto install all the packages needed for replication. To guarantee replicability, you'd need:requirements.txt, which you could generate by making a fresh virtual environment, installing all dependencies known to you (I sawtorchthere), and then runpip freeze > requirements.txt