CS267 Fall 2018Practice Midterm 1

Studying for one of my tests does involve some memorization. I believe this is an important skill. Often people waste a lot of time and fail to remember the things they are trying to memorize. Please use a technique that has been shown to work such as the method of loci. Other memorization techniques can be found off the Wiki Page for Moonwalking with Einstein. Given this, to study for the midterm I would suggest you:

• Know how to do (by heart) all the practice problems.
• Go over your notes at least three times. Second and third time try to see how much you can remember from the first time.
• Go over the homework problems.
• Try to create your own problems similar to the ones I have given and solve them.
• Skim the relevant sections from the book.
• 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. Define the following: (a) probability ranking principle, (b) specificity, (c) exhaustivity.
2. Construct a simple language model based on the following word frequencies for a corpus: bob 3, knows 10, sally 2. Using this model compute the MLE for the phrase: bob knows sally knows.
3. Explain and give a concrete example of smoothing a first order language model with a zeroth order language model.
4. Write a PHP version of the nextPhrase algorithm from class. You can assume functions: next($t, $v, $d), prev($t, $v, $d), first($t, $d), last($t,$d) have already been implemented where the additional argument $d is an inverted index object of some kind. Use the strings "infty" and "-infty" if you go off posting lists.
5. Suppose a posting list for a term `t` for schema-independent index consisted of the numbers 1,3,6,12,88, 480, 1000, 1300, 2500. Explain how the galloping search algorithm from class would compute next(t, 499).
6. Briefly describe the following kinds of inverted indexes: (a) docid index, (b) frequency index, (c) positional index.
7. Explain how the vector space model works. Give an example showing how to compute the cosine similarity between a query vector and a short document of your choice.
8. Step through how the algorithm from class would work to compute nextCover("what", "you", 2) if the corpus consisted of one document containing the phrase: "What you do speaks so loudly that I cannot hear what you say".
9. Briefly explain how the algorithm nextSolution(Q, position) is modified when we allow negations in our boolean queries Q.
10. Define and give an example of calculating each of the following effectiveness measures: (a) Recall, (b) Precision@5, (c) MAP.