In this chapter, we have discussed about word frequencies (unigram, bigram, and trigram). You have studied Maximum Likelihood Estimation and its implementation in NLTK. We have discussed about the interpolation method, the backoff method, Gibbs sampling, and Metropolis-hastings. We have also discussed how we can perform language modeling through perplexity.
In the next chapter, we will discuss about Stemmer and Lemmatizer, and creating the Morphological generator using machine learning tools.