Natural Language Processing

1. Information-theoretic measures of distributional similarity
   • Entropy
   • Cross entropy
   • Kullback-Leibler divergence
   • Jensen-Shannon divergence
2. Text preprocessing using Shell commands
3. Naive Bayes text categorization model
4. Cocke-Younger-Kasami parsing implementation

HW1 - Information-theoretic measures of distributional similarity

• Entropy

* Cross entropy

* Kullback-Leibler divergence

* Jensen-Shannon divergence

HW2 - Text preprocessing using Shell commands

HW3 - Naive Bayes text categorization model

HW4 - Cocke-Younger-Kasami parsing implementation