I manually annotated and tagged contract texts (Organization (Org), Location (Loc), Persons (Per) and Legal Affairs (Jur) ). Now I wanted to do the same with Datamining. I have a dummy classifier that achieves an accuracy of 86.752%. My normal classifier reaches a value of 86.958% and the NER classifier has an accuracy of 76.26% and is therefore not usable.
Since I am a beginner in the subject, I would be interested to know what further usability I have with the classifiers/values?