Word Embedding PL

This repo contains methods which allow to create embeddings based on polish corpora:

OpenSubtitles 2018 pl

ParaCrawl

latest Wikipedia dump

Up to now:

gensim

tensorflow plain model - IN PROGRESS

Name		Name	Last commit message	Last commit date
Latest commit History 9 Commits
language_model		language_model
skipgram		skipgram
Projekt2.ipynb		Projekt2.ipynb
README.md		README.md
create_emb_gensim.ipynb		create_emb_gensim.ipynb
create_emb_tensorflow.ipynb		create_emb_tensorflow.ipynb
utils.py		utils.py
wiki_utils.py		wiki_utils.py

Provide feedback