Please visit, subscribe and share 10 Minutes Lectures in Computer Science

## Natural Language Processing MCQ with answers

### 1. What will be the perplexity value if you calculate the perplexity of an unsmoothed language model on a test corpus with unseen words?

(a) 0
(b) Infinity
(c) any non-zero value
(d) None of the above

### 2. Which of the following NLP tasks use sequential labeling technique?

(a) POS tagging
(b) Named Entity Recognition
(c) Speech recognition
(d) All of the above
 Answer: (d) POS tagging – Given a word sequence W, we need to find the tag sequence T that best matches W. Named Entity Recognition – The typical way to set this up as a sequence labeling problem is called BIO tagging. Each word is labeled B (beginning) if it is the first word in a named entity, I (inside) if it is a subsequent word in a named entity, and O (outside) otherwise. Speech recognition – given a sequence of speech utterance, find the correct word sequence out of many different possible sentences.

### 3. In POS tagging problem, what is the output of Viterbi algorithm?

(a) Probability of word sequence given a particular tag sequence
(b) Optimal transition and observation probabilities for HMM
(c) Probability of the best tag sequence given a word sequence
(d) None of the above

#### Viterbi algorithm used to find the best tag sequence given the word sequence and a HMM model. It uses dynamic programming to arrive at the solution by constructing solutions for the smaller problems.

4. What type of ambiguity exists in the word sequence “Time flies”?
(a) Syntactic
(b) Semantic
(c) Phonological
(d) Anaphoric

### Semantic ambiguity is an uncertainty that occurs when a word, phrase or sentence has more than one interpretation.

5. Let G = (V, T, S, P) be a context-free grammar such that
Variables V = {S, R},
Terminal symbols T = {0, 1}
Productions P = {S → R1R1R1R, R → 0R | 1R |}
Which of the following languages are supported by this grammar?
(a) L = {w | w contains at least three 1’s}
(b) L = {w | the length of w is odd and its middle is 0}
(c) L = {w | w contains more 1's than 0's}
 Answer: (a) As per the productions, there is the rule S → R1R1R1R which consists of three 1’s. Hence, any derivation will consists of strings with at least three 1’s.

*************