5. Question 5 What is the advantage of tokenization (normalize and stemming) before index? 1 point Improves performance by mapping words with similar meanings into the same indexing term…
1. Question 1 Let w1, w2, and w3 represent three words in the dictionary of an inverted index. Suppose we have the following document frequency distribution: Word Document Frequency w1…
2. Question 2 Which of the following is false? 1 point Search engines rely on the text push mode. Recommender systems are based on the text…
9. Question 9 Consider the following retrieval formula: Where c(w, D) is the count of word w in document D, dl is the document length, avdl is the average document…
8. Question 8 Assume the same scenario as in Question 7, but with TF-IDF weighting. Which of the following words do you expect to have the highest weight in this…
3. Question 3 Consider the instantiation of the vector space model where documents and queries are represented as bit vectors. Assume we have the following query and two documents: Q…
10. Question 10 In VSM model, which of the following will be a better way to measure similarity/distance? 1 point Cosine similarity: cos( v_1, v_2 )cos(v1,v2) L2 distance:…
7. Question 7 Suppose we compute the term vector for a baseball sports news article in a collection of general news articles using TF weighting only. Which of the following…
5. Question 5 In the “simplest” VSM instantiation, if instead of using 0-1 bit vectors but we use the word count instead, when we concatenate each document by itself, will…
4. Question 4 Consider the same scenario as in Question 3, with dot product as the similarity measure. Which of the following is true? 1 point Sim(Q,D1) = 4 …
