Abstract—This research aims to extract name entity mentioned in unstructured text into a predefined category using Conditional Random Field (CRF) and bidirectional Long Short-Term Memory (LSTM). The experiments were conducted using one thousand words which extracted from the collection of twitter massage that collected in the topic related to natural disaster and classify into six classes of the output. There are three scenarios for testing and evaluate: CRF, CRF-optimize and a combination of LSTM and CRF. The results show that CRF-optimize parameter performance is given better than other model with 98.94%, 98.95% and 98.93% for precision, recall and F-measure respectively.
 

Index Terms—natural disaster, natural language processing, information extraction, conditional random field, named entity recognition

Cite: Hathairat Ketmaneechairat and Maleerat Maliyaem, "Natural Language Processing for Disaster Management Using Conditional Random Fields," Journal of Advances in Information Technology, Vol. 11, No. 2, pp. 97-102, May 2020. doi: 10.12720/jait.11.2.97-102

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.