Some gist about fasttext:
- Basically 3 packages, wordvector, text classification and compression.
- Text classifications is really comparable with other deep methods. Another Web’s wisdom is here.
- Running the tasks are trivial for proficient unix users. So I don’t want to repeat them here. The examples also run end-to-end and they are fast.
- Unlike what I thought though, fasttext doesn’t quite setup a deep-learning-based word-classification, but as I said, that’s not the point.
- Compression was known to be so good such that it can fit to be embedded devices.
- Users also got granted patents to use the source code freely. So good stuffs.
Some other nice resources one can follow:
http://sebastianruder.com/word-embeddings-1/index.html#continuousbagofwordscbow
http://textminingonline.com/fasttext-for-fast-sentiment-analysis