Quizz 02: Language Modeling

1. Define what is a language model

   
   
   
   
   

2. Explain how a language model can help in the task of spell checking

   
   
   
   
   

3. Write the chain-rule expression of the joint probability p(w1,...,wn)

   
   
   
   
   
   
   

4. What is the Markov assumption applied to language modeling

   
   
   
   
   
   
   

5. How do you estimate the conditional probability p(w|h) where w is a word and h is a sequence of words given a corpus?

   
   
   
   
   
   
   

6. Define the perplexity of a bigram language model given a dataset [w1...wN]

   
   
   
   
   
   
   

7. Define what it means to smooth a distribution estimation.