HMM part-of-speech tagger using the Viterbi algorithm
Implement an HMM part-of-speech tagger using the Viterbi algorithm.
For training use the data in the treebank.5290.train file. Test your
tagger on the sentences provided in the treebank.5290.test file.
a. What is the accuracy of your tagger on the test data?
b. How does this compare to the accuracy obtained by always choosing
the most frequent tag for each word?
c. Identify five errors in the automatically tagged data, and analyse
Note: Both training and test data are available in this directory.
- write a README file including a detailed note about the functionality
of each of the above programs, and complete instructions on how to
run them. Make sure you include the answers to questions a,b,c.
- make sure you include your names in each program and in the README file.
- make sure all your programs are fully commented, and run correctly