dukn / data_volam

create a key-word-dictionary youself

data_volam

Info

Using VNTok (vn.hus.nlp.tokenizer-4.1.1-bin) to tokenize Paragraph.

Using TF-IDF to get "Key word" to create a tinyDict about Game "Vo lam truyen ky web".

• ./vn.hus.nlp.tokenizer-4.1.1-bin/run_by_duc.py to create new data (Data2).

• Using hardcode.py to create datafile.

• Using getDict.py to create file tinyDict.txt

• Enjoy!

Tools

• python

• pandas

• TF-IDF