Is the evaluation metric the same as the ones in the papers?

guillaumegenthial / tf_ner

Simple and Efficient Tensorflow implementations of NER models with tf.estimator and tf.data

Apache License 2.0

923 stars 275 forks source link

Is the evaluation metric the same as the ones in the papers? #52

Closed yuchenlin closed 5 years ago

yuchenlin commented 5 years ago

Hi,

Thanks for making a new version with tf.data and I was wondering if your reported performance is evaluated with the entity-level (i.e. span-level) P/R/F1. It looks like you are using the token-level F1, which can be different from the mainstream span-level metric in the papers.