part of speech tagger on brown corpus data set
Implement a part-of-speech tagger in Python, using Bayesian networks.
The program implements part of speech tagger using following algorithms and compares their accuracy for each sentence:
- Naive inference
- Sampling (Gibbs)
- Approximate max-marginal inference
- Exact maximum a posteriori inference (Viterbi)
- Voting based approach
Commandline: python label.py train_file test_file