fastText VS talk

- trained with cross-entropy, meaning that model scores can be used more effectively as a 'confidence' - e.g. for spam if you want to say something like "if prediction score > X, then filter", Naive Bayes is not ideal due to the 'naive' assumption which makes the scores very un-calibrated (it tends to give extremely high or low confidence scores for most things).

disclaimer: I haven't really thought about NLP for about 3 years so there may be something better than this now

[1] https://github.com/facebookresearch/fastText

fasttext 50

https://github.com/facebookresearch/fastText the readme may have what I need built in. But not sure. I hate ML documentation. I would love to see data input to data output examples because people expect us to understand their line of thought, and it just doesn't work out that way. This looks like what I need, but I've completely misinterpreted ML documentation many times. Ha

To use the model trained with FastText from the browser, it is necessary to load it via WebAssembly. However, you don't require a WebAssembly knowledge as you can use the fasttext.js file which has all the glue code.

Having the backend code in the plugin repo, and in python held me off. I wrote it to split vimscript/python from the command that finds the info, as it allows to use powerful tools like fasttext rather than a dictionary.