Skip to content

Latest commit

 

History

History
21 lines (13 loc) · 493 Bytes

README.md

File metadata and controls

21 lines (13 loc) · 493 Bytes

Text encoding using wordvec

Quick-run text encoding

  1. Compile and quickly generate vector binaries on the small canadianLegal.txt dataset. Feel free to swap with your own textual dataset. The bigger the better results!
$ make
$ ./generateVectorbin.sh
  1. Interactive console to view vector distances of generated vectors.bin file
$ ./distance.out vectors.bin

References

Word2Vec original archive