Rasa Algorithm Whiteboard - BytePair Embeddings

BytePair embeddings are a really cool idea. BytePair Embeddings can be seen as a lightweight variant of FastText. They need less memory because they are more selective in what subtokens they remember. This also makes them useful in certain scenarios because they can ignore subwords as well. They're also available in 275 languages!

If you want to see the Rasa NLU examples repo, go here:

If you want to see the Whatlies repo for these embeddings, go here:

If you want to see the BPEmb repo, go here:

[alanliang]

thanks bro, best explaination i can find.

[faangsde]

This channel is a gold mine! Thank you very much for sharing your insights!

Great video! I think the video description lacks a word in the sentence "They need way memory..."?

[distrologic]

How does the algorithm know when to stop merging tokens?

[piyalikarmakar]

Thanks sir.. one query.. what's the difference between byte pair and wordpiece tokenization?