Manually extracting named entities from ancient Isan medicine texts is time-consuming and requires specialized expertise. Currently, there are no machine learning models specifically developed for this purpose. To bridge this gap, this research paper presents a Named Entity Recognition (NER) model built upon the Conditional Random Field (CRF) method. This model identifies and classifies the names of medicines, diseases, and herbs within these documents. It achieved an accuracy of 96 percent. Additionally, the model was utilized to develop the named entity recognition application. The assessment of this application indicated that is performed at the highest level in all assessed aspects.
No takes yet. Share an insight, caveat, or question.
Jintana Polsri (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: