Language Model

Building a vector space model for Vietnamese.

Author: Nguyen Viet Bac - 22022511

My datatrain is over 100 MB therefore I can't push it to my repo. You can use your data or use the data below:
Data: https://drive.google.com/file/d/1l8PVWLyaFHERQlyleRPyMzxXch-7h-mZ

The project aims to build a vector space for Vietnamese. From this, we use the models to calculate the similarity of words or sentences.

Name		Name	Last commit message	Last commit date
Latest commit History 20 Commits
data		data
model		model
result		result
wikipediacorpus		wikipediacorpus
README.md		README.md
fastText.py		fastText.py
main.py		main.py
make_data.py		make_data.py
requirement.txt		requirement.txt
svd.py		svd.py
using_model_demo.py		using_model_demo.py
visualize.py		visualize.py
word2vec.py		word2vec.py
words		words