New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Work on embedding tuning for medical/pharmacology data #6

Open

strayMat opened this issue Mar 8, 2018 · 0 comments

Collaborator

strayMat commented Mar 8, 2018 •

edited

Loading

Find datasets of french medical/parmacology and train fasttext embeddings on them:

http://opus.nlpl.eu/EMEA.php : concatenation of a lot of medicament documentations in french
Liste des médicaments commercialisés en France au 16-08-17

Use this notebook to construct a training corpus (as for now, the notebook contains only the two precedent sources but we can consider to add more).

Use the fasttext and there cheatsheet to train the embedding.

The fasttext command should be something like :

./fasttext skipgram -input data.txt -output model -pretrainedVectors pretrained -dim 300

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment