org.allenai.nlpstack.parse.poly.eval
Counts the number of tokens "lost" by bad attachments (i.e. their path to the root is different in the gold and candidate parse).
Returns a ratio, typically correctEvents / totalEvents.
a ratio, typically correctEvents / totalEvents
A friendly name for this scoring function.
Counts the number of tokens "lost" by bad attachments (i.e. their path to the root is different in the gold and candidate parse).