SuffolkLITLab / RateMyPDF

RateMyPDF is a website that helps paper form authors (particularly for court forms) improve the usability of their forms for self-represented litigants. It uses the FormFyxer library to deliver its insights.
https://ratemypdf.com
MIT License
1 stars 1 forks source link

Find a version of the Dale-Chall vocabulary list that is able to understand inflections #31

Open nonprofittechy opened 7 months ago

nonprofittechy commented 7 months ago

Currently, even if the root word is easy, an inflection of the word can be marked as difficult. We should change this.

There is an issue that offers suggestions to fix this in the parent library we use, textstat: https://github.com/textstat/textstat/issues/150

nonprofittechy commented 7 months ago

Also check out https://github.com/public-law/readability

nonprofittechy commented 6 months ago

Finally, want to note here that we intend to eventually replace the Dale-Chall wordlist with our own wordlist. So whatever we do with "stemming" should be generalizable.