Questions for Form A

1. The ............distance between the words theorem and theatre is greater than the ............distance.

2. Removing common words (i.e., those on a stoplist), and changing multiple spaces to a single space, are both operations which are usually considered part of the information retrieval process of:

   a.Clustering. b.Filtering. c.Indexing. d.Retrieval.

3. The (term) discrimination value model leads to an algorithm for term:

   a.Broadening. b.Elimination. c.Frequency. d.Narrowing. e.Weighting

4. What is tf * idf ? Why do you think it works well?

5. Explain how ranking can help improve:

   a.Precision. b.Recall.