Machine Assisted Text Annotation Tool is designed to train the machine automatically by using some algorithms for that text which we will input from different sources. It is technique to extract the relationship between neighbouring words in a sentence. This work focuses on the Natural language toolkit (NLTK) library by corpus in the Python environment many problems arise in text annotation. Part of speech (POS) tagging is one technique to minimize those errors, so we will use it in our project. It is a part of the natural language. Parts of Speech (POS) tagging is a text processing technique to correctly understand the meaning of a text. It is the process of assigning the correct POS marker (noun, pronoun, adverb, etc.) To each word in an input text. We use probability-based taggers (models) in this type of problems, because it is most effective. A Hidden Markov Model (HMM) is one of them. HMM is a probabilistic sequence models that can be applied to part of speech tagging. Viterbi algorithm has also implemented in this contest. It provides an efficient way of finding the most likely state sequence in the maximum a posterior probability. We will use python 3.0 for coding, library NumPy for matrix manipulation, pandas for data formatting and manipulation, corpus for NLTK package.