Text analytics ideas + solutions - stopwords for other languages and pre-trained Word2Vec

User 2032 | 8/12/2015, 10:20:42 AM

Hi Guys,

There are some things that should be quite straight forward to do and could give you an age over other text analytics libraries.

First please include stopwords for different languages by default:

You could use these https://code.google.com/p/stop-words/ (free of charge)

Second it would be very cool if you would have pre-trained text feature extractors based on Word2Vec (same as with your recent awesome release of transfer learning for images) for different languages. This idea was inspired by the cool results found here: https://code.google.com/p/stop-words/

Comments

User 19 | 8/12/2015, 2:42:21 PM

Hi JohnnyM,

Thanks for the suggestions! We definitely agree with these ideas, and will add these to our feature request list. Keep the suggestions coming! We'd love to hear more about your text analytics projects to see how else me might be able to help.

Chris