Person Entity Recognition for the Indonesian Qur’an Translation with the Approach Hidden Markov Model-Viterbi

摘要

Qur’an contains teachings about life given by Allah to the Prophet Muhammad. In the Qur’an, there are a lot of verses. With a large number of verses, it will be very difficult and take a long time for us to find a name. Manually searching for entities will be very difficult and take a long time to be searched. With NER, which is one of the techniques of information extraction that aims to detect entity names, such as people’s names, locations, events, and time expected search for entity names in the Qur’an will significantly simplify and shorten the time. Indonesian Qur’an translations will later be used as Inputs, and their names are entity names. The solution to the problem above is to use NER. The Named Entity (NE) Recognition (NER) system will look for name entities people from the corpus that have been created. In applying NER requires a model to detect name entities in a text. Hidden Markov Model-Viterbi is a machine learning algorithm type Supervised Learning which will be applied. In the development of a system for searching names entities for the Indonesian translation of the Qur’an dataset have best F1 results is 76%.