Skip to content

Navigation Menu

Sign in
Sign up
#

hunspell-spell-checker

Here are 7 public repositories matching this topic...

The dataset was first scraped from an Arabic book library website, then cleansed of non-Arabic words, numerals, and tags before going through multiple preprocessing steps. Second, after applying the TF-IDF vectorizer, we used the Random Forest Classifier (RFC) algorithm to be trained on the data. Finally, two Question-Answer datasets were create...

  • Updated Mar 2, 2022
  • Jupyter Notebook

Add this topic to your repo

To associate your repository with the hunspell-spell-checker topic, visit your repo's landing page and select "manage topics."

Learn more

AltStyle によって変換されたページ (->オリジナル) /