Terminology of Combining the Sentences of Farsi Language with the Viterbi Algorithm and BI-GRAM Labeling

Journal of Advances in Computer Research

مقاله 9، دوره 9، شماره 4 - شماره پیاپی 34، بهمن 2018، صفحه 145-155   

نوع مقاله: Original Manuscript

نویسندگان

Ebrahim Akbari^* ؛ Homayun Motameni

Department of Computer Engineering, Sari Branch, Islamic Azad University, Sari, Iran

چکیده

This paper, based on the Viterbi algorithm, selects the most likely combination of different wording from a variety of scenarios. In this regard, the Bi-gram and Unigram tags of each word, based on the letters forming the words, as well as the bigram and unigram labels After the breakdown into the composition or moment of transition from the decomposition to the combination obtained from the types of sentences, the educator is used in 194 different wording types, and the sum of them is obtained by the amount of the advance of each wording state and the MAX value is considered as the output of the system. And at the end, the success rate of these methods and the effectiveness of these two types of labeling are compared with each other.

کلیدواژه‌ها

Viterbi Algorithm؛ Terminology؛ Independent Roles؛ Dependent Roles