search

zhongkaifu / Txt2Vec

Txt2Vec is a toolkit to represent text by vector. It's based on Google's word2vec project, but with some new features, such incremental training, model vector and so on.
BSD 3-Clause "New" or "Revised" License
68 stars 30 forks source link

Train file contents to Txt2Vec #3

Closed My-Khan closed 8 years ago

My-Khan commented 8 years ago

Hello sir, what will be contents/data in train file used in Txt2vec?

  1. only the token/word of original Training file OR
  2. All the data of original training file e.g the Word, POS Tag and NE tag
zhongkaifu commented 8 years ago

If you want to train a word embedding, data #1 is the correct one.

My-Khan commented 8 years ago

ok sir got it.