21 Questions
Retrieval models, algorithms, and systems are not comparable to each other.
False
Relevancy is always a binary judgment, either relevant or not relevant.
False
Determining relevancy of retrieved items is an objective process that does not depend on the user's judgment.
False
The ranking function, term selection, and term weighting components of an IR system are unimportant for evaluating its performance.
False
The number of relevant documents a user needs to find is irrelevant for evaluating an IR system's performance.
False
Dynamic is a term that refers to changes that occur over time.
True
The Cranfield paradigm is a type of experimental science used to evaluate information retrieval systems.
True
Precision is the ratio of the number of relevant documents retrieved to the total number of documents retrieved.
True
Recall is the ratio of the number of relevant documents retrieved to the total number of relevant documents in the collection.
True
The most effective information retrieval system is one that maximizes both precision and recall.
False
RankPower is defined as the average rank of the returned relevant documents.
False
The number of relevant documents, $CN$, is always less than or equal to the total number of returned documents, $N$.
True
In the F-Measure example, the total number of relevant documents is 8.
False
The RankPower formula can be expressed as $\frac{\sum_{i=1}^{CN} L_i}{CN^2}$, where $L_i$ is the rank of the $i$-th relevant document.
True
For R=3/6 and P=3/4, the F-Measure calculated is 0.5
True
In the second example, the RankPower is higher than in the first example.
False
The RankPower metric does not take into account the number of relevant documents returned.
False
In the parameterized F-Measure formula, when β > 1, precision is weighted more.
True
Precision @ 5 and Precision @ K are two different metrics used in Information Retrieval.
False
Mean Average Precision (MAP) is a measure used in information search systems like web search.
True
Normalized DCG (NDCG) stands for Direct Cumulative Gain.
False
Test your knowledge on performance evaluation of information retrieval systems including system evaluation, ranking functions, term selection, term weighting, and difficulties in evaluating IR systems effectiveness.
Make Your Own Quizzes and Flashcards
Convert your notes into interactive study material.
Get started for free