Checking for differences in overregularization rates between male and female children
In collaboration with Charles Yang and Kyle Gorman, I have developed a Python package to identify correct past-tense tokens and overregularized tokens in the CHILDES database. Using this information, we investigate the reported differences in overregularization rates between male and female children.
-s, --scriptdir (default "scripts/")
-t, --tagger (default NLTK)
-x, --overwrite (false)
-o, --outputdir (default "output_$TAGGERNAME")