Andrew Tavis McAllister

DeepL also has a [Python client](https://www.deepl.com/en/blog/announcing-python-client-library-for-deepl-api) that could be a good fit for this.

@AhmetCakar, hi again :) You could certainly try BERT without removing the n-grams, but I've found that kwx works better when they're removed. BERT is able to pick up semantics...

Hi @Eman-2021-PhD :) Thanks for your compliments and your questions! First question: I'm assuming that the code that you're referring to is the imports at the top of [examples/kw_extraction](https://github.com/andrewtavis/kwx/blob/main/examples/kw_extraction.ipynb), but...

You're very welcome!

Hi @Eman-2021-PhD :) `method="frequency"` is just going to return the words that occur the most in the documents, which can be considered to be keywords in a simplistic sense. One...

You're very welcome, and further regards!

Hi Abhishek, The necessity to have a corpus to compare for TFIDF comes from the "IDF" part - Inverse Document Frequency. The way that kwx works is that everything that...

A further explanation on this: if you look at my package [wikirec](https://github.com/andrewtavis/wikirec), there we're using TFIDF to find the terms that appear more frequently in any given Wikipedia article when...

Sounds good :) Thanks for your interest!

Hi @christopherpickering :) Wanted to bring https://github.com/mdn/content/pull/17138 to your attention in relation to this feature request. The original PR was based on H017 from djlint, with the consensus being that...