wordvectors icon indicating copy to clipboard operation
wordvectors copied to clipboard

What tokenizer for Bahasa?

Open kenyeung128 opened this issue 7 years ago • 3 comments

Hi, might i ask which tokenizer do u use for Bahasa (Indonesia)? Thanks.

kenyeung128 avatar Jul 31 '17 08:07 kenyeung128

I didn't use any extra tokenizer for Indonesian because Indonesian contains spaces.

Kyubyong avatar Aug 01 '17 01:08 Kyubyong

Bahasa fasttext vector embedding link is broken , can help to upload ?

sathik11 avatar Sep 13 '17 02:09 sathik11

Actually all the fasttext vector links were broken, which I don't know why. I've just updated them. Thanks.

Kyubyong avatar Sep 13 '17 11:09 Kyubyong