search

FelipeLuz / dotnet-bad-word-detector

.NET library that uses machine learning to detect bad words (profanity) within a string.
Apache License 2.0
14 stars 1 forks source link

Feat: Add support for Spanish and English #4

Open pval99 opened 6 months ago

pval99 commented 6 months ago

Hi Felipe, as I said in the issue I am adding the sources for English and Spanish profanity words. I double checked them and they are commonly accepted bad words since profanity is subjective. It would be nice if you could train the model or give a guide in the README to expand the library. Thanks!

FelipeLuz commented 6 months ago

Hey @pval99 I'll be adding it today, thanks for the help mate.

pval99 commented 6 months ago

Nice, @FelipeLuz should we be retraining Enlgish with the new list? Moreover, I wanted to ask if the model trains for word variations with uppercase or number substitution.

FelipeLuz commented 6 months ago

@pval99 I was thinking about keeping the English model the same for consistency, and yes the new Spanish model takes into account small variations on words like the original English model.

pval99 commented 5 months ago

Nice @FelipeLuz this branch should be ready to merge.