· web viewcourse r2016 date of examination 13/10/2020 branch: computer engineering sem: viii...

100 Sample Questions for B.E. Examination (A.Y. 2019-2020)

“These are sample MCQs to indicate pattern, may or may not appear in examination”

Course R2016

Date of Examination 13/10/2020

Branch: Computer Engineering

Sem: VIII

Subject Name (with Subject Code): DLO8012: Natural Language Processing

Total Modules 1,2,3,4,5,6

Number of questions: 100

Q. No. 1.

Many words have more than one meaning; selecting the sensible meaning in context is done with

a)

Randomization

b)

Shallow semantic analysis

c)

Word Sense Disambiguation

d)

POS tagging

2.

Which statement is true



a)

Rule based methods are language independent

b)

Stochastic methods are language independent

c)

It is highly complex task to resolve ambiguities especially at lower levels of NLP

d)

Disambiguation task are is more challenging in Resourceful language as compared to Resourceless language

3. What is a meaning of Morphology?

(a) The study of word format

(b) The study of sentence format

(c) The study of syntax of sentence

(d) The study of semantics of sentence.

4. What is morpheme?

(a) Set of words with grammar.

(b) Smallest linguistic unit with grammatical function.

(c) Set of rules.

(d) Smallest sentence with syntax.

5. Which of the following is the example of surface segmentation?

(a) Achievability = achievabil + ity

(b) Achievability = achiev + ability

(c) Achievability = Achieve + able + ity

(d) Achievability = achiev + abil + ity

6. Which derivational prefixes does not change the category of word to which they are attached?

(a) Re- & -Un



(b) -er

(c) -ize

(d) -ing

7. Which one of the following is morpheme of the word “unbelievable”?

(a) un

(b) unbe

(c) evable

(d) able

8. Which of the following is correct example of stem “replayed”?

(a) Replay

(b) Play

(c) Played

(d) Replayed

9. Which python library use to implement natural language processing?

(a) NLTK

(b) Scrapy

(c) Matplotlib

(d) Pydot

10. Following are the basic regular expression patterns, which one is incorrect pattern?

(a) Disjunction

(b) Caret

(c) Ranges

(d) Conjunction

11. “I almost bought an Acura Integra today, but a door had a dent andthe engine seems noisy.”This is an example of which type of referring expression(a) Reflexive

(b) Gender Agreement

(c) Inferrable

(d) Selectional Restriction

12. Lappin and Leass Algorithm is used for

(a) Coherence Relation

(b) Pronoun Resolution

(c) Anaphora Resolution

(d) Syntax Analysis



13. Porter Stemmer algorithm use for _______.

(a) Lemmatization

(b) Syntax Analysis

(c) Stemming

(d) Part of speech tagging

14. Regular expressions are combination of simple units as given in options, select incorrect unit.

(a) Character or string

(b) Concatenation

(c) Kleen star

(d) Conjunction

15. Which of the following example is the type of free morphemes?

(a) Dog

(b) Un-(unhappy)

(c) Re-(Reschedule)

(d) -y(smiley)

16. How to compute probability of a sentence or sequence of sentence in N-gram model?

(a) P(W) = P(W1,W2, W3,…, Wn)

(b) P(W) = P(Wn+1|Wn-1)

(c) P(W) = P(Wn-1| Wn+1)

(d) P(W) = P(Wn+1 | Wn)

17. What is significance of caret ^ in regular expression?

(a) If [ab ^ cd] means “ a or b ^ c and d”.

(b) If [^A-Z] means all uppercase nothing negated.

(c) If caret is first symbol after the open square brace “[” then resulting pattern is negated.

(d) If [^a-b] means all lowercase nothing negated.

18. What is a difference between Finite State Automata (FSA) and Finite State Transducers (FST)?

(a) FSA contain single tape and FST also contain single tape.

(b) FSA contain single input tape and FST contain single output tape.

(c) FSA contain single input tape and FST contain input: output pair tapes.

(d) Both FSA and FST contains output tapes only.

19. Which of the following is not a primitive operation of a regular expression?(a) Concatenation

(b) Closure

(c) Union

(d) Projection



20. Format of words is given in options, select incorrect option.

(a) Books Book + Noun + Plural

(b) Shopping Shop + Verb + Cont.

(c) Cats Cat + Verb

(d) Wentgo + Verb + Past

21. How conditional probability rewrite in language model?P(B | A) =P(A, B) / P(A)(a) P(A, B) = P(A) P(B | A)

(b) P(A, B) = P(A) P(A | B)

(c) P(A, B) = P(B) P(B | A)

(d) P(A) = P(A) P(B | A)

22. How given sentence represented using Bigram model?“I want to eat Indian food”(a) {(I, want), (want, to), (to, eat), (eat, Indian),(Indian, food)}

(b) {(I ), (want, to), (to, eat), (eat, Indian),(Indian, food),(food, I)}

(c) {(I, want, to), (want, to, eat), (to, eat, Indian), (eat, Indian, food)}

(d) {(I), (want), (to), (eat), (Indian), (food)}

23. Which of the following are Anchors in regular expression?

(a) * and +

(b) ^ and $

(c) ? and {}

(d) \d and \w

24. A DFA is a tuple A = (Q, ∑, δ, qo, F) ,what does δ indicates?

(a) Finite set of state

(b) A finite set of input symbols

(c) Transition function

(d) A set of final states

25. Which one of the following is type of spelling errors?

(a) Sentence errors

(b) Non-word errors

(c) Non-cognitive errors

(d) Syntax errors

26. Mini-Corpus given, <s>I am Sam <s> <s>Sam I am<s> <s> I do not like green eggs and ham<s>What will be bigram probability of P(am | I)?



(a) 0.67

(b) 0.33

(c) 0.5

(d) 0.25

27. Which token of the following is lemmatized correctly by the rule given?(X) –sses -ss(X) –ies -i(X) –ss -ss (X) –s ϵ(a) Buses

(b) Dogs

(c) Dog

(d) Courses

28. The word “Putting” is handle and clean up by which stemming rule?“Putting Put”(a) {(X) –ing ϵ} and {--CC C}

(b) {(X) –eed -ee} and {-at -ate}

(c) {(X) –ing -ing}

(d) {(X) –C1VC2 C1VC2e}

29. Which of the following is the example of overstemming?

(a) Univers

(b) Universe

(c) Universal

(d) University

30. Which of the following is the example of understemming?

(a) Data

(b) Date

(c) Datum

(d) Dat, Datu

31. Which are the consonants in a given string?“SYZYGEO”(a) S, Z, G

(b) Y, E

(c) Y, O

(d) S, Y, O, Z, G

32. Rule for removing suffix will be given in form “(Condition) S1 S2”, where S1 is suffix.If the condition is “(*d)” then which of the following is correct interpretation?



(a) The stem ends with S.

(b) The stem contain vowel.

(c) The stem ends with a double consonant (eg. -TT, -SS)

(d) The stem ends CVC, where second C is not W, X, or Y

33. Alice was beginning to get very tired of sitting by her sister on the bank, and of having nothing to do: once or twice she had peeped into the book her sister was reading, but it had no pictures or conversations in it, `and what is the use of a book,' thought Alice `without pictures or conversation?'Which among the options is NOT a coreferrring expression?

(a) Alice, her(b) Alice, she(c) Book, her(d) Book, it

34. Which of the following is a example of irregular noun form?a) Fox

b) Dog

c) Mouse

d) Cat

35. What is Syntax Analysis?

(a)This only abstracts the dictionary meaning or the real meaning from the given context.

(b) This component transfers linear sequences of words into structures. It shows how the words areassociated with each other.

(c) It deals with the overall communicative and social content and its effect on interpretation. It means abstracting or deriving the meaningful use of language in situations.

(d)

It focuses about the proper ordering of words which can affect its meaning. This involves analysis of the words in a sentence by following the grammatical structure of the sentence. The words are transformed into the structure to show how the words are related to each other.

36. Syntactic analysis or parsing may be defined as the process of ________ the _______ of symbols inNatural language conforming to the rules of formal grammar.

(a) Analyzing & Strings

(b) Defining & Groups

(c) Reducing & Arrays

(d) Reviewing & Letters 37. Following property is of - .These taggers are knowledge-driven

(a) Rule based Tagging

(b) Stochastic Tagging



(c) Rule based Tagging and Stochastic Tagging

(d) Neither Rule based Tagging nor Stochastic Tagging 38. Following property is of - .This POS tagging is based on the probability of tag occurring

(a) Rule based Tagging

(b) Stochastic Tagging

(c) Rule based Tagging and Stochastic Tagging

(d) Neither Rule based Tagging nor Stochastic Tagging39. Where the additional variables does are added in HMM?

a)Temporal model

b)Reality model

c)Probability model

d)In all three models, temporal, reality and probability model

40.. How does the state of the process is described in HMM?

a)Literal

b)Single random variable

c)Single discrete random variable

d)Literal and Single random variable

41. HMMs are “a statistical Markov model in which the system being modeled is assumed to be a________process with ________ states”.

a)Convolution, completed

b)Markov, Unobservable

c)Analyzing, Categorized

d)Complete, Observed

42. What is the major difference between CRF (Conditional Random Field) and HMM (Hidden Markov Model)?

(a) CRF is Generative whereas HMM is Discriminative model

(b) CRF is Discriminative whereas HMM is Generative model

(c) Both CRF and HMM are Generative model

(d) Both CRF and HMM are Discriminative model

43. HMM are designed to model the joint distribution P(H , O) , where H is the _____state and O is the________ state

(a) Hidden, Observed

(b) Unobservable, Hidden

(c) Classified, Completed



(d) Open, Completed

44. HMM graphs consist of a Hidden Space and Observed Space, where the hidden space consists ofthe _______ and the observed space is the ______

(a) Input, Categories

(b) Values, Variables

(c) Labels, Input

(d) Variables, Values

45. HMMs are limited to only ________ states and only take into account the last known _____.

(a) Complete, Value

(b) Unobserved, Variable

(c) Hidden, Attribute

(d) Discrete, State

46. Maximum Entropy Markov Models use a maximum entropy _______for _______ and local __________.

(a) Framework, Features, Normalization

(b) Rules, Variables, Classification

(c) Sets, Values, Distribution

(d) Rules, features, classification

47. In the context of POS tagging, the objective would be to build an HMM to model P(____ | ___) andCompute the label probabilities given observations using _____ Rule.

(a) Value, Label, Markov

(b) Word, Tag, Bayes

(c) Attribute, Variable, Bayes

(d) Input, Label, Markov

48. In HMMs, spaces are connected via ______ matrices {T,A} to represent the probability of ________ fromone state to another following their _____

(a) Transitions, Transitioning, Connections

(b) Attribute, Changing, groups

(c) Label, moving, sets

(d) Attribute, moving, sets

49. Each connection in HMM represents a _______ over possible options; given our ______, this results ina large search space of the ________ of all words given the tag.



(a) Value, variables, associativity

(b) Distribution, tags, probability

(c) Variable, Labels, Transitivity

(d) Object, groups, associativity

50. Consider the statement: "Ban on dancing on Governor's desk. " would be interpreted as:

(a) (Ban (on dancing)) (on Governor's desk)

(b) (Ban on ((dancing) on Governor's desk)

(c) (Ban (on dancing on Governor's desk))

(d) (Ban on (dancing ) on ((governor’s)) desk)

51. Parts-of-Speech tagging determines ___________ . 1) part-of-speech for each word dynamically as per meaning of the sentence2) part-of-speech for each word dynamically as per sentence structure3) all part-of-speech for a specific word given as input

(a) Only 1 is correct

(b) 1 and 2 are correct

(c) 1 and 3 are correct

(d) All (1,2 and 3) are correct.

52. In an HMM, observation likelihoods measure

(a) The likelihood of a POS tag given a word

(b) The likelihood of a POS tag given the preceding tag

(c) The likelihood of a word given a POS tag

(d) The likelihood of a POS tag given two preceding tags

53. Solve the equation according to the sentence “I am planning to visit New Delhi to attend Analytics Vidhya Delhi Hackathon”. A = (# of words with Noun as the part of speech tag)B = (# of words with Verb as the part of speech tag)C = (# of words with frequency count greater than one)

What are the correct values of A, B, and C?

(a) 5,5,2

(b) 5,5,0

(c) 7,5,1

(d) 7,4,2



54. Two words with very closely related meanings(a) Antonyms

(b) Homonyms

(c) Synonyms

(d) Hyponymy

55. Focus on what the words conventionally mean, rather than on what an individual speaker might think they mean, or want them to mean, on a particular occasion; concerned with objective or general meaning and avoids trying to account for subjective or local meaning

(a) semantic features

(b) semantic analysis

(c) Semantic roles

(d) semantics

56. Polysemy is a Greek word, which means(a) Many names

(b) Many signs

(c) Many meanings

(d) Many verbs

57. Which of the following is not correct with respect to levels of semantic analysis?(a) Word level

(b) Character level

(c) Sentence level

(d) Utterance level

58. Which of the following is not correct with respect to Word Sense Disambiguation (WSD)(a) It offers sense definitions of words

(b) Identifies synsets of synonyms

(c) Defines a number of semantic relations

(d) It’s not free

59. Phrase structure riles are of the form A->BC which states that

(a) A is directed towards BC

(b) A implies B and C



(c) Constituents A can be written as two constitutes B and C

(d) BC holds value of A

60. A prepositional phrase consists of a preposition and its(a) Object

(b) Subject

(c) Noun

(d) Verb

61. "We always play football after work." Which is a prepositional phrase?

(a) Always play football

(b) After work

(c) Always play

(d) Football after

62. "The tour includes three Asian countries." Which is a noun phrase?(a) The tour includes

(b) three Asian countries

(c) Three asian

(d) Tour includes

63. two or more words with the same form and related meanings by extension (foot of a person, of a bed, of a mountain); based on similarity

(a) Metonymy

(b) Hyponymy

(c) Polysemy

(d) Hyponym

64. Homophones for the word piece(a) Peace

(b) Conflict

(c) Noise

(d) Irritation

65. Car is hyponym of



(a) Scooter

(b) Cycle

(c) Rickshaw

(d) Automobile

66. Dog is hyponym of

(a) Forest

(b) Human

(c) Animal

(d) Automobile

67. Mango is hyponym of(a) Forest

(b) Human

(c) Fruits

(d) Sweet

68. The words Blood bank, Sperm bank and Egg bank are the example of,(a) Polysemy

(b) Hypernym

(c) Antonym

(d) Metonymy

69. Software designed for taking i/p data(text) and give structural representation of the input after checking the correct syntax or grammar is(a) Compiler

(b) Parser

(c) Painter

(d) Easydraw

70. Two words are there with same spelling as “magazine”. One has meaning as something you read and another is cartridge to store bullets for a gun. However both words senses are related as to store or save somewhere. This is an example of

(a) Metonymy

(b) Hyponymy



(c) Polysemy

(d) Hyponym

71. Two words are there with different spelling but sound is same wring(1) and wring(2). First one means to twist something and second one means you wear in your finger. This is an example of(a) Homonymy

(b) Hyponymy

(c) Polysemy

(d) Homophony

72. The statement “Time passes very quickly” can be represented as(a) AdvP->(Intens) NP

(b) AdvP->(Intens) Adv

(c) N->Wh-NP VP

(d) S->Wh-NP VP

73. The statement “Which team won the match?” can be represented as(a) N->Wh-NP VP

(b) S->Wh-NP VP

(c) VP->Wh-NP VP

(d) S->Wh-NP NP

74. The statement “Which mobiles can you show me in your shop?” can be represented as(a) N->Wh-NP Aux NP VP

(b) S->Wh-NP Aux NP NP

(c) S->Wh-VP Aux NP VP

(d) S->Wh-NP Aux NP VP

75. The statement “ eat a pizza” can be represented as

(a) NP → Verb VP

(b) VP → Verb PP

(c) VP → Verb NP

(d) VP → Verb NP PP

76. What is the right order for the steps in the process of Sentiment Analysis 1. Identify each sentiment bearing phrase and component



2. Break each text document into its component parts3. Combine scores for multi layered sentiment analysis4. Assign a sentiment score to each phrase and component

(a)1,2,3,4(b)2,1,4,3(c)3,1,2,4(d)2,3,1,4

77. What is the right order for the steps in a basic Question Answering system 1. Onto Triplets generation and Ontology traversal2. Tokenization and word grouping3. Chunking4. POS Tagging

(a)2,1,3,4(b)1,3,2,4(c)3,1,2,4(d)2,4,3,1

78. In a collection of M documents, one document is selected randomly. The document contains a total of N terms and the term “NLP” appears L times.What is the correct value for the product of TF (term frequency) and IDF (inverse-document-frequency), if the term “data” appears in approximately one-fourth of the total documents?(a) LN * Log(4)(b)L * Log(4) / N(c)N * Log(4) / L(d)Log(4) / LN

79. What is the right order for an extraction based text summarization approach1. Gather text documents with positively labeled key phrases2. Extract merited key phrases from source document3. Carry out classification for all key phrase words4. Train a binary machine learning classifier

(a)1,2,3,4(b)2,1,4,3(c)3,4,2,1(d)2,3,1,4

80 Which of the following is not a technique to build a Sentiment Lexicon(a) Manual



(b) Corpus based(c)Dictionary based(d) Machine learning

81. Sentiment classification deals with automatically tagging text into categories except one(a)Positive(b)Negative(c)Neutral(d)Useless

82. ‘The movie is directed by Nolan’ will be classified as (a)Positive(b)Negative(c)Neutral(d)Useless

83. ‘ The movie is entertaining and totally worth your money’ will be classified as(a)Positive(b)Negative(c)Neutral(d)Useless

84. ‘ The movie is so boring I was dozing away throughout’ will be classified as(a)Positive(b)Negative(c)Neutral(d)Useless

85. Sentiment Analysis does not deal with (a)Analyzing emotions of a speaker(b) Analyzing feelings of a speaker(c) Analyzing attitude of a speaker(d) Analyzing physical appearance of a speaker

86. The target of Sentiment Analysis does not deal with



(a)Find opinions (b)Identify sentiments(c)Classify polarity(d)Rate the polarity

87. Which of the following is not a classification level in Sentiment Analysis(a)Word level(b)Sentence level(c) Document level(d)Aspect level

88. Which of the following is not an example of Question Answering System(a)Siri(b)Cortana(c) Google Search(d)Google Now

89. Alice has built a text classifier with Naive Bayes algorithm. The training data is given in the table. Now Alice gets a new test document “kola kola yarrow”. Suppose the probability of getting a test document is 1/K where K is a constant. According to the trained classifier, in which class this document will belong to and what will be the probability?

Doc Words Class1 Hazel kola Nut2 Macadamia kola pecan Nut3 Amaranth yarrow flower4 Yarrow dianthus kola Flower

(a)nut, 3.472 * K * 10-3

(b)flower, 2.604 * K * 10-3

(c)nut, 2.604 * K * 10-3

(d)flower, 3.472 * K * 10-3

90. You want to buy a new mobile this Diwali and lots of reviews about new mobiles are avilable. So you decide to use Text summarization method to find out what is people's opinion in general about a product. What kind of summarization method would you use to understand the reviews? 1. Extractive multi document summarization2. Abstractive multi document summarization3. Extractive single document summarization4. Abstractive single document summarization(a) 3,4



(b) 1,2(c) 1,4(d) 2,3

91. Using SentiWordNet 3.0 find out the no of Synsets in which the word “unable” belongs to. Also find out the positivity, negativity and objectivity scores for unable (a,3) where a represents “adjective” i.e. the POS tag of the word. (a)No. of synsets:4, PosScore:0.125, NegScore:0.25, ObjScore: 0.625(b) No. of synsets:3, PosScore:0.125, NegScore:0.25, ObjScore: 0.625(c) No. of synsets:3, PosScore:0, NegScore:0.375, ObjScore: 0.625(d) No. of synsets:3, PosScore:0, NegScore:0.75, ObjScore: 0.25

92. Sentiment lexicons can be learned using intuitions such as:(a)Same polarity words are connected by “and”(b)Opposite polarity words are connected by “but”(c)Same polarity words are connected by “but”(d)Same polarity words are connected by “and” and Opposite polarity words are connected by “but”

93. Which metric was employed by Turney Algorithm to measure co-occurrence?(a)Point wise Mutual Algorithm(b)Jaccard Coefficient(c)Jensen-Shannon Divergence(d)Dice coefficient

94. Let P (w|c) represent the probability of a word given its rating. Further let P (w) represent the probability of the word in the overall corpus. While analyzing the polarity of a word in a given corpus what is the intuition behind dividing P(w|c) by P(w)? (a)To make it comparable across different ratings(b) To make it comparable across different words(c) To make it comparable across different documents(d) To make it comparable across different sentences

95. Polarity shift technique is used to handle(a)False positives(b)False negatives(c)Normalization problems(d)Negations



96. Your friend Alice has got the transcripts for the Finance’s Ministers press meet. She wants to summarize the minister’s opinion on recent financial reforms. Which of the following summarization methods should she apply? 1. Abstractive query focused 2. Abstractive generic 3. Extractive query focused 4. Extractive generic(a)3,4(b)1,2(c)1,3(d)2,4

97. Statistical approach of ambiguity resolution in NLP isa) Primary approach b) Design approach c) Graphic approach d) Probabilistic model approach

98. Which of the following is application of Natural language processing concern with Marathi to Hindi translatora) Speech recognition b) Language translator c) Information retrieval d) Question answering system

99. Which of following is discourse level ambiguitya) Anaphoric b) Contextual c) Situation d) Semantic

100. Consider the system generated summary (S) and reference summary (R) as followsS: nut is a fruit composed of an inedible hard shell and an edible seedR: nut is a fruit with hard shell and an edible seedWhat is the Rouge-2 -recall and Rouge-2 -precision?(a)0.667 and 0.462(b)0.600 and 0.429



(c)0.875 and 0.500(d)0.601 and 0.785

· web viewcourse r2016 date of examination 13/10/2020 branch: computer engineering sem: viii...

Documents