Common English morphemes, organized for automated access.
The vision of this project is the creation of a resource that not only segments words into prefixes, roots/stems, and suffixes, but also associates meanings with these affixes. This is in contrast to the many resources out there that focus only on segmentation.
Entries, grouped by "meaning", are contained in the file morphemes.json in the data folder. Currently, the Python scripts provided operate on one word at a time, and integrate with the NLTK package.
See the README files in both folders for more detail. Any comments and suggestions are appreciated.