Join GitHub today
GitHub is home to over 40 million developers working together to host and review code, manage projects, and build software together.Sign up
Misidentifying corporations as persons #15
I parsed a list of the top 100 Cook County property tax bill recipients (by number of PINs they receive bills for).
All persons – by my review – were identified correctly as Person, but the following 8 names were mistakenly identified as persons:
hey @stevevance - thx for trying it out!
I'll add BAFCO & HOMEWERKS-LAMONT to the training data as corporations, but for the other 6 strings, I'm not sure what the 'true' labels would even be. thoughts?
this library can parse name/household/corporation input strings, but doesn't verify whether a string is a name/household/corporation vs none of the three.
The scope of probablepeople is to parse names, not identify names. So
We won't handle