Skip to content
Discussion options

You must be logged in to vote

Yes, the NER architecture uses features likes NORM and SHAPE which are both case-sensitive. The pre-trained models are not 100% accurate, and mistakes like these can happen. We have a master thread for these cases.

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by thomashacker
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
feat / ner Feature: Named Entity Recognizer perf / accuracy Performance: accuracy
2 participants