1.

Which of the following techniques can be used for the purpose of keyword normalization, the
process of converting a keyword into its meaningful base form?
A. Lemmatization B. Levenshtein distance C. Morphing D. Stemming

2. Which of the following areas where NLP can be useful?

A. Automatic text summarization B. Automatic question answering systems
C. Information retrieval D. All of the above

3. Valid Markov assumptions are

A. The probability of a word depends only on the current word.
B. The probability of a word depends only on the previous word.
C. The probability of a word depends only on the next word.
D. The probability of a word depends only on the current and the previous word.

4. For the string ‘mash’, identify which of the following set of strings have a Levenshtein
distance of 1.
A. smash, mas, lash, mushy, hash B. bash, stash, lush, flash, dash
C.smash, mas, lash, mush, ash D. None of the above

5. What is the part of speech tag for the word "quickly" in the sentence "She quickly finished her
homework."?
A. Adverb B. Verb C. Noun D. Adjective

6. ____________ ambiguity exists in the presence of two or more possible meanings of the
sentence within a single word.

7. _____________ is the process of removing the inflections of a word in order to map the word
to its root form.

8. _____________________smoothing technique is most complex.

9. Perplexity will be infinite because unseen words will get _____ probability.

10. The part of speech tag for the word "the" in the sentence "The cat slept on the mat." is
_______________

11. Match the following NLP phase with its description:

P. Lexical Analysis A. Divides text into paragraphs, sentences, and words and
converts it into meaningful lexemes
Q. Parsing B. Checks grammar, word arrangements, and shows the
relationship among words
R. Semantic Analysis C. Concerned with the literal meaning of words, phrases,
and sentences
S. Pragmatic Analysis D. Helps to discover the intended effect by applying a set
of rules that characterize cooperative dialogues.

A. P-A,Q-B,R-C,S-D B. P-D,Q-B,R-C,S-A C. P-B,Q-A,R-C,S-D D. P-A,Q-C,R-B,S-D

12. Match the term to its definition:
P.Syntax A.describe the structure of a language
Q.Grammar B. rules governing the way words combine to form sentences
R.Productions C. define how the elements of a language can be combined to form
sentences
A. P-A, Q-B, R-C B. P-C, Q-B, R-A C. P-B,Q-A,R-C D. P-A,Q-C,R-B

13. Match the example to its category:

P. I love to read books in my free time. A. Declarative sentence
Q. Could you pass me the salt, please? B. Interrogative sentence
R. After I finish my homework, I can play outside. C. Complex sentence

A. P-A, Q-B, R-C B. P-C, Q-B, R-A C. P-B,Q-A,R-C D. P-A,Q-C,R-B

14.Which boolean operation can be represented by a multilayer perceptron?

A. X1 AND X2 B. X1 OR X2 C. X1 NOR X2 D. X1 XOR X2
P.D only Q.C and D only R.A,B and C only S. A,B,C and D only

15. Match the example to its models.

P.Unigram A. P(so)
Q.Bigram B. P(so|is)
R.Trigram C. P(so|water is)

A. P-A, Q-B, R-C B. P-C, Q-B, R-A C. P-B,Q-A,R-C D. P-A,Q-C,R-B

16. The Noisy Channel Model in NLP is only applicable to speech recognition and language
translation.
A.True B. False
17. Ambiguity in NLP is the state of being ambiguous usually with more than one interpretation
of a word, phrase or sentence.
A.True B. False
18. Models that assign probabilities to sequences of words are called language models.
A.True B. False
19. We normalize the counts of words in an n-gram model to make the value to fall between 0
and 1.
A.True B. False
20. The part of speech tag for the word "happy" in the sentence "She was happy to see her
friends." is adjective.

A.True B. False
1. Imagine you are designing a system for a customer service chatbot. Your client wants the
chatbot to efficiently answer customer queries in natural language. Which application of Natural
Language Processing would be most suitable for this task?
A. Spam Detection B. Question Answering C. Sentiment Analysis D. Machine Translation

2. Suppose you are developing an NLP tool for a research project aiming to extract information
from research papers. What would be the primary purpose of implementing information
extraction in your NLP system?
A. Converting spoken words into text B. Detecting unwanted e-mails in a user's inbox
C. Extracting structured information from unstructured or semi-structured machine-readable
documents. D. Analyzing the attitude and emotional state of the sender

3. Assume that we modify the costs incurred for operations in calculating Levenshtein
distance, such that both the insertion and deletion operations incur a cost of 1 each, while
substitution incurs a cost of 2. Now, for the string ‘lash’ which of the following set of strings
will have an edit distance of 1?

A. ash, slash, clash, flush B. flash, stash, lush, blush,

C. slash, last, bash, ash D. None of the above

4. Suppose you are evaluating the performance of a language model on a test corpus containing
unseen words. What would be the likely outcome in terms of perplexity if the language model is
unsmoothed?
A. 0 B.Infinity C. any non-zero value D.None of the above

5. Imagine you are analyzing the sentence "I am running late for my appointment." What part of
speech tag would you assign to the word "running" in this context?
A. Adverb B.Verb C. Noun D. Adjective

6. ______________type of ambiguity exists in the phrase “Time flies”?

7. In the sentence, “They bought a blue house”, a blue house is an example of
______________phrase.

8. _______ many bi-grams can be generated from the given sentence: India is my country.

9.Markov assumption states that the probability of a word depends only on the
__________________word.

10. The part of speech tag for the word "beautiful" in the sentence "The sunset was beautiful" is
____________

11. Match the following NLP phase with its description:

P. Lexical Analysis and Morphological A. Divides text into paragraphs, sentences, and words
and converts it into meaningful lexemes
Q. Syntactic Analysis (Parsing) B. Checks grammar, word arrangements, and shows the
relationship among words
R. Semantic Analysis C. Concerned with the literal meaning of words, phrases,
and sentences
S.Discourse Integration D. Depends on the sentences that precede it and also
invokes the meaning of the sentences that follow it
A. P-A,Q-B,R-C,S-D B. P-D,Q-B,R-C,S-A C. P-B,Q-A,R-C,S-D D. P-A,Q-C,R-B,S-D

12. Match the term to its definition:

P.Syntax A.The set of rules that describe the structure of a language
Q.Grammar B. The study of the rules governing the way words combine to form
sentences
R.Production rules C. set of rules that define how the elements of a language can be combined
to form sentences
A. P-A, Q-B, R-C B. P-C, Q-B, R-A C. P-B,Q-A,R-C D. P-A,Q-C,R-B

13. Match the example to its category:

P.John walked to the store. A.Interrogative sentence
Q.The cat in the hat sat on the mat. B.Complex sentence
R.Who is going to the party? C.Simple sentence
A. P-A, Q-B, R-C B. P-C, Q-B, R-A C. P-B,Q-A,R-C D. P-A,Q-C,R-B

14.Which Boolean operation can be represented by a single layer perceptron?

A. X1 AND X2 B. X1 OR X2 C. X1 NOR X2 D. X1 XOR X2
P.D only Q.C and D only R. A,B and C only S. A,B,C and D only

15. Match the example to its models.

P.Unigram A. P(the)
Q.Bigram B. P(the/that)
R.Trigram C. P(the/transparent that)
A. P-A, Q-B, R-C B. P-C, Q-B, R-A C. P-B,Q-A,R-C D. P-A,Q-C,R-B

16. The Noisy Channel Model in NLP is only applicable to speech recognition and language
translation.
A.True B. False

17. The outputs of Lemmatization and Stemming for the same word might differ.
A.True B. False

18. A 3-gram model is a 2 order Markov Model.

A.True B. False

19. A small number of words occur with high frequency.

 A.True B. False

20. In a match between India and Australia during the ICC World Cup 2023, the commentator
remarked, "The striker kicked the ball with incredible precision." The appropriate part of speech
tag for the word 'kicked' in this sentence is Verb.

A.True B. False

1. What is NLP? Discuss the various phases involved in NLP process with suitable example.

2. What do you mean by ambiguity in natural language? Explain with suitable example.

3. Explain the various applications of NLP.

4. Explain Damerau-Levenshtein edit distance. Compute the minimum edit distance between
actress, cress, caress, access, across, acres, acres with respect to acress.

5. Construct a parse tree for the sentence “all the morning flights from Denver to Tampa leaving
before 10”.

6. Consider the following corpus C12 of 4 sentences. What is the total count of unique bi-
grams for which the likelihood will be estimated? Assume we do not perform any pre-
processing.

today is Kohli’s birthday

he likes ice cream

he is also fond of cream cake

we will celebrate his birthday with ice cream cake

7. Consider the following corpus C2 of 3 sentences.

there is a big garden

 children play in a garden

they play inside beautiful garden

Calculate the perplexity of <s> they play in a big garden </s> assuming a bi-gram language
model.

8. Given a corpus C3, the Maximum Likelihood Estimation (MLE) for the bigram “dried
berries” is 0.4 and the count of occurrence of the word “dried” is 680. for the same corpus
C3, the likelihood of “dried berries” after applying add-one smoothing is 0.05. What is the
vocabulary size of C3?

9. Can neural units compute simple functions of input like AND, OR, and XOR? Justify.

10. Explain the working principle of Feedforward Neural Network

11. With example, explain the various closed classes in English.

12. Describe the various Part-of-speech tags in English.