Indonesian Named Entity Recognition on An Employment Complaint Letter Using Machine Learning

Yan Puspitarani

Abstract


This study determines the feature as a criterion for predicting the Named Entity(NE) in the labor complaint
document. Seven elements are resulting from the feature extraction process for the NE classification process.
This feature will be divided into three test cases in the classification. The classification process uses a variety of
machine learning algorithms to determine which algorithm produces the best performance. The results show that
Gradient Boosted Trees delivers the best performance based on accuracy.


Keywords


Feature Extraction, Machine Learning, Named Entity Recognition

Full Text: PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.