CS267 Fall 2012Practice Midterm 1

To study for the midterm I would suggest you: (1) Know how to do (by heart) all the practice problems. (2) Go over your notes at least three times. Second and third time try to see how much you can remember from the first time. (3) Go over the homework problems. (4) Try to create your own problems similar to the ones I have given and solve them. (5) Skim the relevant sections from the book. (6) If you want to study in groups, at this point you are ready to quiz each other. The practice midterm is below. Here are some facts about the actual midterm: (a) It is closed book, closed notes. Nothing will be permitted on your desk except your pen (pencil) and test. (b) You should bring photo ID. (c) There will be more than one version of the test. Each version will be of comparable difficulty. (d) One problem (less typos) on the actual test will be from the practice test.

1. What is the probability ranking principle (PRP)? Suppose we have the urls http://www.youtube.com, http://youtube.com, http://www.reelseo.com/youtube-seo-tips/. Use PRP to rank these urls with respect to the query "youtube". Explain your reasoning.
2. Explain and give an example of how to compute the maximum likelihood estimate of a phrase based on a language model for terms in a vocabulary.
3. Explain how a language model can be modified to give a positive probability to terms not in the original vocabulary. Why would you want to do this?
4. Give an example Markov Model in which it is possible to generate the string "The chicken and the egg" from state 1. Show how to calculate the probability of this phrase from state 1 in your model.
5. Give pseudocode for implementing the nextPhrase function based on the next() and prev() functions of our ADT.
6. Give pseudocode for implementing the next() function in our inverted index ADT using galloping search.
7. Explain what information each of the following kinds of indexes store: (a) docid index, (b) frequency index, (c) positional index.
8. Suppose the word zwaggered appears four times in our corpus and appears twice in document 7. Suppose our corpus has 16 documents. What would be the TF-IDF score for zwaggered in document 7.
9. Document 8 consists of the phrase "do be do be do". Calculate its proximity score for the phrase "do be".
10. What is MAP? Give an example of how to calculate a MAP score.