Unigram

Unigram (plural unigrams) (linguistics) An n-gram consisting of a single item from a sequence. Unigram — a probability-based model.It calculates the probability of every subword token and then drops it based on a loss function that is explained in this research paper. Based on a certain threshold of the loss value, you can then trigger the model to drop the bottom 20–30% of the subword tokens.

• https://github.com/UnigramDev/Unigram
• https://www.youtube.com/watch?v=Bh-PE9nCE4g
• https://www.youtube.com/watch?v=f9aRzT5jaaM
• https://web.stanford.edu/~jurafsky/slp3/3.pdf
• https://www.nltk.org/api/nltk.lm.html#nltk.lm.api.Smoothing