What is the next goal and what is the problem?

by sharete   Last Updated July 13, 2019 01:26 AM

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?



Related Questions


TF-IDF formula used in RapidMiner

Updated June 14, 2018 06:26 AM


Issues in getting trigrams using Gensim

Updated September 11, 2017 10:26 AM

Similarity of a group of text documents

Updated May 19, 2017 06:26 AM

data mining with unstructured data how to implement?

Updated October 18, 2017 04:26 AM