Skip to content

Latest commit

 

History

History
12 lines (8 loc) · 399 Bytes

README.md

File metadata and controls

12 lines (8 loc) · 399 Bytes

Turkish Word2Vec

My attempt to create a word2vec model with Turkish data. Modified version of this tutorial.

Data source: YTU Kemik TEAM - 42K News

TODO

  • Better text preprocessing.
  • Find a larger dataset (TR Wiki Dump?).
  • Tune parameters (num of epochs, window size etc.)