A modern programming language that makes developers happier.

kotlinlang

<@U8SBFSF2B>  why not using transformers for that NLP task?

HMMs are simpler, fast and you can apply them to a ton of other things. They are more universal. POS is just one of the multitude of applications. Transformers will give you better results, sure, and I plan to write about them at some point later, but this time I was in the mood to write about a probabilistic approach. As simple as that.

And HMMs contain a lot less parameters and thus can be trained faster with less data.

You don't need to retrain the whole model. Just use those already packaged by huggingface or Google

On GPU they are pretty fast enough to run. Even spacy starts to move away from probabilistic models

Delivering those to Kotlin is very much on the plan here

There are many sparse training data situations in time-series analytics (beyond NLP) where no base model for transfer learning is available, and there HMMs are a great tool. And when in doubt it's always worth starting with a simpler model unless metrics prove it wrong.