4. Information Retrieval & Relational Databases

Question 1

What is Information Retrieval?

Answer 1

Finding documents that are about a given topic

Question 2

What is a corpus?

Answer 2

An organised repository, or collection, of data

Question 3

What is relevance?

Answer 3

Whether a retrieved document is actually about the requested topic

Question 4

What is precision?

Answer 4

The probability that a document is relevant given that it is retrieved
i.e Number of relevant documents retrieved / total number of documents retrieved

Question 5

What is recall?

Answer 5

The probability that a document is retrieved given that is is relevant
i.e Number of relevant documents retrieved / total number of relevant documents

Question 6

How would we compare IR algorithms? (2)

Answer 6

• Average precision, which attempts to combine trade-off between precision and recall into a single value
• Effectiveness measure, which combines precision and recall into a single value

Question 7

What is Average Precision? (2)

Answer 7

• Reflects the recognition that precision varies, expressing the variation as a graph (curve) of precision vs. recall
• Attempts to summarize curve as single value for comparison

Question 8

What is Effectiveness Measure algorithm?

Answer 8

1 - 1 / a(1/P) + (1-a)(1/R)
a: alpha, 0=precision isn’t important, 1=recall isn’t important
P: Precision
R: Recall