Named Entity Recognition for Characteristic of Medical Herbs Using Modified HMM Approach
The amount of articles in medicinal herbs is very huge. It is performed with unstructured format so that it takes time to get information as reader’s need. Therefore, this research purposes to recognize the name entity of article from internet in order to increase information retrieval or other analysis data purposes. Named entity recognition is one of the goals of information extraction which is to identify the name and characteristics of the herbs. This paper is propose the modified method of Hidden Marcov Model (HMM) with Viterbi algorithm. In this method, it is enclosed gazetteer list for labeling name and location of data training to construct HMM. The data sets are taken from three web sites including: miliaton, aliweb, and plants. As a result, the performance is achieved at average precision value of 0.93, recall of 0.83 and f-measure of 0.85.
(1) Alfred, R., Leong, L.C., Kim On, C., Antony, P., et.al. (2013). Named Entity Recognition for Malay Articles. Lecture Notes in Computer Science (LNCS, Volume 8346. pp:288-299).DOI: 10.1007/978-3-642-53914-5_25
(2) Todorovic, B.T., Rancic, S.R., Markovic, L.M., Mulalic, E.H., Dan Ilic, V.M. (2008). Named Entity Recognition And Classification Using Context Hidden Markov Model . Symposium On Neural Network Applications In Electrical Engineering. Neurel-2008.
(3) Suwarningsih, W., Supriana, I., and Purwarianti, A.(2014). Imner Indonesian Medical Named Entity Recognition. 2nd International Conference On Technology, Informatics, Management, Engineering & Environment.
(4) Sumathy, K.L., Chidambaram, M. (2013). Text Mining: Concept, Applications, Tools and Issues- An Overview. International Journal of Computer Applications (00975-8887). Volume 80(4).
(5) Fauzi, M.A., Arifin, A.Z. and Yuniarti, (2017). An Arabic Book Retrieval using Class and Book Index Based Term Weighting. International Journal of Electrical and Computer Engineering (IJECE). Volume 7(6)
(6) David Nadeau, Satoshi Sekine , “A survey of named entity recognition and classification” National Research Council Canada / New York University
(7) Lin, J. Dan Dyer, C. (2010). Data-Intensive Text Processing with Mapreduce. Available https://Lintool.Github.Io/Mapreducealgorithms/Mapreduce-Book-Final.Pdf
(8) Viterbi, A. (1967). Optimum decoding algorithm for convolutional codes. In IEEE Trans. Info. Theory (supported by AFOSR)
(9) Padmaja Sharma, Utpal Sharma, Jugal Kalita. (2011), “Named Entity Recognition: A Survey for the Indian Languages”.