It is to keep in mind that the 99% accuracy is reported after being tested from the corpora/test_en.py and is subject to the dataset of CELEX English morphology word forms only.
Coverage decreased (-0.6%) to 67.706% when pulling e4ea51b5538a3b43e7dd532ec592d1afeaab3ca0 on kyscg:patch-1 into 5b85d998c30ddc6772b56310713530224466083a on clips:master.
Fix for #141 , #175 , #176
And fixed typo in metrics.py