After completing this experiment, students will be able to:

1. Understand Smoothing in N-gram Models: Explain the need for smoothing in N-gram language models and describe common smoothing techniques.
2. Apply Add-One Smoothing: Calculate smoothed bigram probabilities using Add-One (Laplace) Smoothing.
3. Analyze Sparse Data: Identify and address the issue of zero-probability N-grams in sparse bigram tables.
4. Compare Probability Distributions: Observe and interpret the effects of smoothing on probability distributions in N-gram models.
5. Practice with Interactive Simulation: Gain hands-on experience by filling in bigram probability tables and checking answers interactively.

Learning Focus

• Apply Add-One Smoothing to bigram tables
• Understand the impact of smoothing on language model probabilities
• Address zero-probability issues in sparse data
• Practice probability calculations in an interactive environment