toolbox for various tasks in the area of vector space models of computational linguistic
VSMlibs helps to perform a range of tasks within a framework of vector space models of computational linguistics.
What functionality is included
- creating word embeddings by counting and neural-based methods, including sub-word-level models
- importing and exporting from a banch of popular formats of word embeddings and providing unified access to word-vectors
- perfroming a range of downstream tasks / benchmarks on embeddings
- visualising embeddings
How do I get set up?
- pip3 install vsmlib for stable version
- pip3 install git+https://github.com/undertherain/vsmlib.git for latest dev version
- Python 3.5 or later is required
|Tutorial||vsmlib overview and end-to-end examples.|
|API Reference||The detailed reference for vsmlib API.|
|Contribute||How to contribute to the vsmlib project and code base.|
Who do I talk to?
- Issue tracker is the way to go