Module

Details Contents

1.
Introduction
History of NLP, Generic NLP system, levels of NLP , Knowledge in
language processing , Ambiguity in Natural language , stages in
NLP, challenges of NLP ,Applications of NLP
2.
Word Level Analysis
Morphology analysis –survey of English Morphology, Inflectional
morphology & Derivational morphology, Lemmatization, Regular
expression, finite automata, finite state transducers (FST)
,Morphological parsing with FST , Lexicon free FST Porter
stemmer. N –Grams- N-gram language model, N-gram for
spelling correction.
3.
Syntax analysis
Part-Of-Speech tagging( POS)- Tag set for English ( Penn
Treebank ) , Rule based POS tagging, Stochastic POS tagging,
Issues –Multiple tags & words, Unknown words. Introduction to
CFG, Sequence labeling: Hidden Markov Model (HMM), Maximum
Entropy, and Conditional Random Field (CRF).
4.
Semantic Analysis
Lexical Semantics, Attachment for fragment of English-
sentences, noun phrases, Verb phrases, prepositional phrases,
Relations among lexemes & their senses –Homonymy, Polysemy,
Synonymy, Hyponymy, WordNet, Robust Word Sense
Disambiguation (WSD) ,Dictionary based approach
5.
Pragmatics
Discourse –reference resolution, reference phenomenon ,
syntactic & semantic constraints on co reference
6.
Applications
(preferably for
Indian regional
languages)
Machine translation, Information retrieval, Question answers
system, categorization, summarization, sentiment analysis,
Named Entity Recognition

______________________________________________________----------------------------------------------
NLTK stands for _____.

a. Natural Language Toolkit.

b. Neutral Lingual Tool
c. Natural Language Tool
d. Neutral Language Toolkit

2. NLP is a subfield of _______.

a. Artificial Intelligence
b. Machine Learning
c. Deep Learning
d. None of Above

3. What is Sentiment Analysis?

a. Gathering data of emojis on social media posts.
b. None.

c. recognizing the sentiment among several online posts and comments using NLP.

d. recognizing the sentiment among several online posts and comments using NLTK.

4. Examples of NLP?

a. Digital assistance, chatbots, Text summarization, text retrieval, sentiment analysis,

translation etc.
b. Clustering and differentiating patterns.
c. Deep Learning, Machine Learning, AI etc.
d. None of Above.

5. Likely, which languages can be used to work with NLP?

a. Python & R language.

b. JavaScript
c. Assembly
d. React Js.

6. When the first patents for "translating machines" were applied?

a. After 1945

b. Mid 1930
c. Mid 2000
d. Before 1930

7. Who discovered “Turing Test”?

a. Alan Turing
b. Venessa Turing

8. NLP breaks down language into shorter, more basic pieces, called _____.
a. Parameters

b. Tokens.
c. None.
d. Arguments.

9. What are the components of NLP?

a. Morphological and Lexical Analysis, Syntactic Analysis, Semantic Analysis, Discourse

Integration, Pragmatic Analysis
b. Only Morphological and Lexical Analysis.
c. Only Semantic Analysis
d. All of Above

10. What is Morphical and Lexical Analysis?

a. It depicts analyzing, identifying and description of the structure of words. It includes

dividing
a text into paragraphs, words and the sentences.
b. This component transfers linear sequences of words into structures.
c. This only abstracts the dictionary meaning or the real meaning from the given context.
d. All of Above.

11. Semantic Analysis means _____.

a. It depicts analyzing, identifying and description of the structure of words. It includes dividing
a
text into paragraphs, words and the sentences.

b. This component transfers linear sequences of words into structures. It shows how the
words
are associated with each other. And focuses only on the literal meaning of words, phrases,
and sentences.
c. deals with the overall communicative and social content.
d. None of Above

12. What Pragmatic Analysis does?

a. This component transfers linear sequences of words into structures.
b. This only abstracts the dictionary meaning or the real meaning from the given context.
c. This component transfers linear sequences of words into structures. It shows how the words
are
associated with each other.

d. 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.
13. 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
are
associated 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.

14. Discourse Integration means _____.

a. It means a sense of the context. The meaning of any single sentence which depends
upon those sentences. It also considers the meaning of the following sentence.
b. It depicts analyzing, identifying and description of the structure of words. It includes dividing
a
text into paragraphs, words and the sentences.
c. This component transfers linear sequences of words into structures. It shows how the words
are
associated with each other. And focuses only on the literal meaning of words, phrases,
and
sentences.
d. All of Above.

15. How to implement NLP?

a. Machine Learning & Statistical Inference.

b. Machine Learning & AI
c. Deep Learning
d. Python & R

16. What are the approaches of NLP?

a. Morphological and Lexical Analysis,Syntactic Analysis, Semantic Analysis,Discourse
Integration,
Pragmatic Analysis

b. Symbolic, Statistical, Connectionist and Hybrid

c. Machine Learning, Deep Learning & AI
d. None of These.

17. What Symbolic Approach performs?

a. This component transfers linear sequences of words into structures. It shows how the words
are
associated with each other. And focuses only on the literal meaning of words, phrases,
and
sentences
b. It harnesses various mathematical techniques and often uses large text corpora to
develop
approximately generalized models of linguistic phenomena based on actual examples.

c. It performs extensive analysis of linguistic phenomena through explicit representation

of facts about language and well-understood knowledge representation schemas and
associated algorithms.
How does the Statistical Approach work?

a. It uses statistical methods to resolve some of the difficulties in symbolic approach. It

does this by harnessing various mathematical techniques and often using large text
corpora to develop approximately generalized models of linguistic phenomena based
on actual examples.
b. It performs extensive analysis of linguistic phenomena through explicit representation of
facts
about language and well-understood knowledge representation schemas and associated
algorithms.
c. It harnesses various mathematical techniques and often uses large text corpora to
develop
approximately generalized models of linguistic phenomena based on actual examples.
d. All of the above

19. Connectionist Approach is based on_____.

a. The interconnection of networks having simple processing units with knowledge stored
in weights to identify connections between units.
b. It performs extensive analysis of linguistic phenomena through explicit representation of
facts
about language and well-understood knowledge representation schemas and associated
algorithms.
c. It harnesses various mathematical techniques and often uses large text corpora to
develop
approximately generalized models of linguistic phenomena based on actual examples.
d. None of Above

20. Symbolic Approach is also called _____.

a. Convolutional Neural Networks.

b. Rule based Approach.

c. Corpus based.
d. Hybrid.

21. Statistical Approach is also called____.

a. Corpus Based Approach.
b. Rule Based Approach
c. CNN
d. K- nearest

22. Connectionist Approach is widely known as___.

a. Statistical
b. Symbolical

c. Neural Network
d. All of above

23. What kind of ambiguities are faced by NLP?

a. Lexical and syntactical
b. NLP does not face any ambiguity.
c. semantical, discourse and Pragmatic.

d. Both a & c

24. What is Lexical Ambiguity?

a. Ambiguity of a single word when it can be used as a verb, noun or an adjective.

b. Words having many meanings.
c. Sentences and words are not aligned.
d. All of the above.

25. What scope ambiguity involves?

a. Operators and quantifiers

b. Parameters and arguments
c. Tokens
d. None of Above.

26. When semantic ambiguity occurs?

a. when the meaning of the words themselves can be misinterpreted.

b. Words having many meanings.
c. Both a & b
d. None of the above.

27. What pragmatic ambiguity refers?

a. It refers to a situation where the context of a phrase gives it multiple interpretation

b. It refers to Statistical analysis
c. It refers to only Misinterpreted words
d. All of the above

28. What is corpus?

a. A corpus is collection of Parameters and arguments

b. A corpus is a large and structured set of machine-readable texts that have been
produced in a natural communicative setting.
c. It refers to a situation where the context of a phrase gives it multiple interpretation

29. ______________ depicts analyzing, identifying and description of the structure of words.
a. Tokens
b. Semantic Analysis
c. Symbolic Analysis

d. Morphical And Lexical Analysis

30. _____________ includes dividing a text into paragraphs, words and the sentences.

a. Morphological and Lexical Analysis

b. Semantic Analysis
c. Quantifiers
d. None of the above.

31. _____________ transfers linear sequences of words into structures.

a. Semantic Analysis
b. Tokens
c. Lexical Analysis
d. Discourse
32. _______________ shows how the words are associated with each other.

a. Semantic Analysis
b. Tokens
c. Lexical Analysis
d. Discourse

33. _______________ focuses only on the literal meaning of words, phrases, and sentences.
a. Morphological and Lexical Analysis

b. Semantic Analysis
c. Quantifiers
d. None of the above.

34. ________ deals with the overall communicative and social content and its effect on
interpretation.
a. Tokens

b. Pragmatic Analysis
c. Symbolic Analysis
d. Morphical And Lexical Analysis

35. ____ means abstracting or deriving the meaningful use of language in situations.
a. Semantic Analysis
b. Tokens
c. Lexical Analysis

d. Pragmatic Analysis

36 .It focuses about the proper ordering of words which can affect its meaning.

a. Syntax Analysis
b. Semantic Analysis
c. Lexical Analysis
d. Pragmatic Analysis

37. This involves analysis of the words in a sentence by following the grammatical
structure of the
sentence.
a. Tokens
b. Lexical Analysis
c. Discourse

d. Syntax Analysis

38. The words are transformed into the structure to show how the words are related to each
other. This
process is called as ____________

a. Syntax Analysis
b. Semantic Analysis
c. Lexical Analysis
d. Pragmatic Analysis

39. ____means a sense of the context. The meaning of any single sentence which depends upon
those sentences. It also considers the meaning of the following sentence.

a. Discourse
b. Semantic Analysis
c. Lexical Analysis
d. Pragmatic Analysis

40. Machine Learning & Statistical Inference are the popular methods for implementing___.
a. Lexical Analysis
b. Tokens and Quantifiers

c. NLP

d. None of the above.

41. It performs extensive analysis of linguistic phenomena through explicit representation of

facts about language and well-understood knowledge representation schemas and associated
algorithms. What
is it?
a. Convolutional Neural Networks.

b. Rule based Approach.

42. It uses statistical methods to resolve some of the difficulties in symbolic approach. It
does this by harnessing various mathematical techniques and often using large text
corpora to develop approximately generalized models of linguistic phenomena based on actual
examples.
a. Convolutional Neural Networks.
b. Rule based Approach.
c. Corpus based.

d. Statistical Approach

43. The interconnection of networks having simple processing units with knowledge stored in
weights
to identify connections between units.
a. Connectionist Approach
b. Neural Networks
c. Hybrid approach

d. Both a & b.

44. Rule Based Approach is also called _____________

a. Convolutional Neural Networks.

b. Symbolic Approach.
c. Corpus based.
d. Hybrid.

45. Corpus Based Approach is also called _________

a. Statistical Approach.
b. Rule Based Approach
c. CNN
d. K- nearest

46. Neural Networks are also known as ___________

a. Statistical
b. Symbolical
c. Connectionist Approach
d. All of above

47. Ambiguity of a single word when it can be used as a verb, noun or an adjective is called as
________

a. Lexical Ambiguity
b. Pragmatic Ambiguity
c. Semantic Ambiguity
d. None of Thes
48. Operators and Quantifiers are mostly responsible for ___________

a. Scope Ambiguity
b. Pragmatic Ambiguity
c. Semantic Ambiguity
d. None of These

49. when the meaning of the words themselves can be misinterpreted then ______ ambiguity
occurs.
a. Scope Ambiguity
b. Pragmatic Ambiguity

c. Semantic Ambiguity
d. None of These

50. What refers to a situation where the context of a phrase gives it multiple interpretations?
a. Lexical Ambiguity
b. Scope Ambiguity
c. Semantic Ambiguity

d. Pragmatic Ambiguity

51. What is Morphological Analysis?

a. Morphological analysis is the process of providing grammatical information about the

word on the basis of properties of the morpheme it contains.
b. This component transfers linear sequences of words into structures.
c. This only abstracts the dictionary meaning or the real meaning from the given context.
d. All of Above.

52. What are the components of Morphological Analyzer acc., to Shrivastava et. al 2005?

a. The recognition engine, identifying suffixes, and finding a stem within the input
word algorithms
b. Morpheme lexeme, Set of rules governing the spelling and composition of
morphologically
complex words & Decision algorithm
c. The recognition engine, set of rules & Algorithm.
d. All of the above.

53. Morphological analyzer is composed of the following Three parts according to Kumar, 2013?
a. The recognition engine, identifying suffixes, and finding a stem within the input word
algorithms

b. Morpheme lexeme, Set of rules governing the spelling and composition of

morphologically complex words & Decision algorithm
c. The recognition engine, set of rules & Algorithm.
d. All of the above
54. Morphological analysis is also known as___.
a. Sentiment Analysis
b. Pragmatic Analysis
c. CNN
d. Lexical Analysis

55. What are the various methods of Morphological Analysis?

a. Finite State Automata (FSA),Two level Morphology, Finite State Transducer(FST),
b. Stemmer Algorithm, Corpus based Approach, DAWG(Directed Acyclic Word Graph)
c. Paradigm based approach

d. All of the above

56. What is FSA (Finite State Automata)?

a. Finite state automaton is a model of behavior composed of state, transitions and
actions.
b. This consists of rules which map the two representations to eachother.Each rule is
described
through a finite-state transducer
c. It takes raw corpus as input and produces a segmentation of the word forms observed in the
text.
d. None of the above

57. _____ is a model of behaviour composed of state, transition and actions.

a. FST

b. FSA
c. DAWG
d. Stemmer Algorithm

58. The lexical representation of a word-form is also called as_____.

a. Morphophonemic
b. Morphotacties
c. Both a & b
d. None of the above

59. ______has given a computational model of two-level morphology for word-form

recognition and generation in his dissertation in 1983.
a. Kumar
b. Shrivastava

c. Kimmo Koskenniemi
d. Chomsky

60. The two-level morphology model consists of two representations and one rule. What are
they?

a. The surface representation of a word-form, The lexical representation of a word-form,

rules which map the two representations.
61 .The surface representation of a word-form, The lexical representation of a word-form,
rules which

map the two representations refers to ______.

a. Two-level morphology model

b. Chomsky Model

c. Finite State Automata

d. Both a & c

62. _____is an advanced version of FSA(finite state automata)and is used to represent the
lexicon computationally.

a. FST
b. FSA

c. DAWG

d. Stemmer Algorithm

63. Finite State Transducer is an advanced version of _____ and is used to represent the
lexicon

computationally.

a. FST

b. FSA
c. DAWG

d. Stemmer Algorithm

64. In FST what components are used to build morphological analysers?

a. lexicon, orthographic rules and spelling variations

b. The surface representation of a word-form, The statistical representation of a word-form, rules

which map the two representations.

c. Lexicon, The statistical representation & spelling variations

d. None of the above.

65. lexicon, orthographic rules and spelling variations are the components of ______.

a. Stemmer Algorithm
b. Two-level morphology

c. FST
d. FSA

66. An FST is simply a classical finite-state automaton whose transitions are ____ , rather than
with single
symbols.
a. Labeled with tokens

b. labeled with pairs

c. Not labeled
d. Both a & b

67. What is stemmer?

a. This consists of rules which map the two representations to eachother.Each rule is
described
through a finite-state transducer
b. It takes raw corpus as input and produces a segmentation of the word forms observed in the
text.

c. It is used for stripping of affixes. It uses a set of rules containing a list of stems
and replacement rules.
d. All of the above

68. The most widely used stemmer algorithm is _____.

a. Potter Algorithm

b. Porter Algorithm
c. Decision Algorithm
d. Both a & b

69. _____ used for stripping of affixes. It uses a set of rules containing a list of stems and
replacement rules.
a. Two-level morphology model
b. Chomsky Model
c. Finite State Automata
d. Stemmer

70. What is corpus?

a. A corpus is collection of Parameters and arguments
b. Corpus is a large collection of written text belonging to a particular language
c. It refers to a situation where the context of a phrase gives it multiple interpretation
d. All of the Above.

71. DAWG stands for ______.

a. Directed Acyclic World Graph
b. Directed Acyclic Word Graph
c. Directed Acrylic Word Graph
d. Diverse Acyclic Word Graph

72. DAWG is ___.

a. It is a very efficient data structure for lexicon representation and fast string matching
with a great variety of applications.
b. It is a very efficient data structure.
c. It is used for representation.
d. All of above

73. A ____ defines all the word forms of a given stem and also provides a feature structure with
every word
form. The _____ is efficient for inflectional rich languages.
a. Paradigm, paradigm-based approach
b. Paradigm based approach, paradigm
c. Paradigm, rule-based Approach
d. None of the above

74. The ANUSAARAKA research group has developed a language independent paradigm
based morphological compiler program for ____. This or a variant of this scheme has been used
widely in NLP.
a. European Languages
b. English Languages
c. Indian Languages
d. All of the above

75. The _______research group has developed a language independent paradigm based
morphological compiler program for Indian languages. This or a variant of this scheme has been
used widely in NLP.
a. ANUSAARAKA
b. Anusarka
c. ANUSARKAR
d. All of the above

76. Morphology is divided into two branches:

a. Direct, Indirect
b. Inflectional
c. Derivational
d. Both b & c

77. _____is a change in word form. This usually means the use of endings. For eg., He works, he
worked, and he is working
a. Derivational Morphology
b. Inflectional Morphology
c. Both a & b
d. None of the above

78. ________creates new words. For example, beauty becomes beautiful. The affix -ful changes the
word from a noun to an adjective.
a. Derivational Morphology
b. Inflectional Morphology
c. Both a & b
d. None of the above

79. ____________ morphology uses many more affixes than ____morphology.

a. Inflectional, derivational
b. Derivational, inflectional
c. Direct, Indirect
d. None of the above

80. NLTK have following stemming classes:

a. Porter Stemmer, Lancaster Stemmer
b. Regexp Stemmer
c. Snowball Stemmer
d. All of the above

81. In _____, the words are replaced by the root words or the words with similar context.
E.g.- Walking will be replaced by Walk(walk is the root word of walking)
a. Stemming
b. Lemmatization
c. Both a & b
d. None of the above

82. ____are created by removing the suffixes or prefixes used with a word. This process is called
as____
a. Stems, Stemming
b. Lemma, Lemmatization
c. Corpus
d. Suffix stripping

83. NLTK requires Python versions above__.

a. 2.7
b. 3.8
c. 3.0
d. 2.0

84. A _____, often called a pattern, specifies a set of strings required for a particular purpose. A
simple way
to specify a finite set of strings is to list its elements or members.
a. Regular Expression

b. Non regular Expression

c. Finite Automata
d. None of the above

85. a|b* denotes

a. {ε, "a", "b", "aa", "ab", "ba", "bb", "aaa", ...}
b. {ε, "a", "b", "bb", "bbb", ...}
c. {"a", "ac", "ab", "abc", "abb", "abbc", ...}
d. None of the above

86. (a|b)* denotes

a. {ε, "a", "b", "aa", "ab", "ba", "bb", "aaa", ...}
b. {ε, "a", "b", "bb", "bbb", ...}
c. {"a", "ac", "ab", "abc", "abb", "abbc", ...}
d. None of the above

87. ab*(c|ε) denotes

a. {ε, "a", "b", "aa", "ab", "ba", "bb", "aaa", ...}
b. {ε, "a", "b", "bb", "bbb", ...}
c. {"a", "ac", "ab", "abc", "abb", "abbc", ...}
d. None of the above

88. (aa)*(bb)*b denotes

a. {b, aab, aabbb, aabbbbb, aaaab, aaaabbb, …………..}
b. {ε, "a", "b", "aa", "ab", "ba", "bb", "aaa", ...}
c. {"a", "ac", "ab", "abc", "abb", "abbc", ...}
d. None of the above

89. (0 + 10*) denotes

a. {1, 01, 10, 010, 0010, …}
b. { 0, 1, 10, 100, 1000, 10000, … }
c. {ε, 0, 1, 01}
d. None of the above

90. ____is the simplest machine to recognize patterns. It has a set of states and rules for moving
from one
state to another but it depends upon the applied input symbol.
a. Finite Automata
b. DFA
c. NFA
d. None of the above

91 .What is Q in the finite automata set?

a. Finite set of states.
b. set of Input Symbols.
c. Initial state.
d. set of Final States.

92. Σ denotes in Finite Automata set as:

a. Finite set of states.
b. set of Input Symbols.
c. Initial state.
d. set of Final States.

93. FA is characterized into two types & they are:

a. DA, NA
b. NFA, DFA
c. Both a & b
d. None of these

94. In ___null (or ε) move is not allowed.

a. NFA
b. DFA
c. Cyclic graphs
d. None of the above

95. In ____null (or ε) move is allowed i.e., it can move forward without reading symbols.
a. NFA
b. DFA
c. Cyclic graphs
d. None of the above

96. What FS transducers do?

a. It is a finite state automaton which produces output as well as reading input, it is useful
for parsing.
b. It is the simplest machine to recognize patterns.
c. A simple way to specify a finite set of strings is to list its elements or members.
d. All of the above

97. Transducers work in 4 modes. What are they?

a. generation mode,recognition mode,
b. translation mode(left to right), translation mode(right to left)
c. Both a & b

8. What is generation mode?

a. It accepts when the word on the first tape consists of exactly as many as as the word on the
second tape consists of bs.
b. It reads as from the first tape and writes an b for every a that it reads onto the second tape.
c. It writes a string on one tape and a string on the other tape. Both strings have
the same length.
d. It reads bs from the second tape and writes an a for every f that it reads onto the first tape.

99. What recognition mode does?

a. It accepts when the word on the first tape consists of exactly as many as the word on
the second tape consists of.
b. It reads as from the first tape and writes an b for every a that it reads onto the second tape.
c. It writes a string of as on one tape and a string bs on the other tape. Both strings have the
same length.
d. It reads bs from the second tape and writes an a for every f that it reads onto the first tape.

100. What are the advantages of Porter stemmer algorithm?

a. Produces the best output as compared to other stemmers.Less error rate.
b. Compared to Lovins it’s a light stemmer.
c. The Snowball stemmer framework designed by Porter is language independent
approach to
stemming
d. All of the above.

101. The ______ algorithm is a process of removing suffixes from words in English.
a. Lovins Stemmer
b. Porter Stemmer
c. paice/ Husk Stemmer
d. None of the above

102. Disadvantages of Porter Stemming algorithm are:

a. The stems produced are not always real words.
b. It has at least five steps and sixty rules and hence is time consuming
c. It writes a string on one tape and a string on the other tape. Both strings have the same length.
d. Both a & b

103. The _____ is a very interesting method and it is language independent.

a. Lovins Stemmer
b. Porter Stemmer
c. paice/ Husk Stemmer
d. N-Gram Stemmer
104. N-Gram stemmer has following advantages:
a. Based on the concept of n-grams and string comparisons.
b. Language independent.
c. Both a & b
d. None of the above

105. Limitations of N-Gram Stemmer are:

a. Not time efficient.
b. Requires a significant amount of space for creating and indexing the n-grams.
c. Not a very practical method
d. All of the above

106. _________ is a vocabulary, a list of words, a dictionary.

a. Corpus
b. WordNet
c. Lexicon
d. None of the above

107. ______________ is a lexical database for the English language.

a. Corpus
b. WordNet
c. Lexicon
d. None of the above

108. __________ basically, means a body, and in the context of Natural Language Processing (NLP),
it means a body of text.
a. Corpus
b. WordNet
c. Lexicon
d. None of the above
109. What are the applications of FST?
a. Word Inflections. For example, pluralizing words (cat -> cats)
b. Morphological Parsing; i.e., extracting the “properties” of a word (e.g., computers -> computer
+ [Noun] + [Plural])
c. Simple Word Translation, e.g., translating US English to UK English
d. All of the above.

110. ______are general rules used when breaking a word into its stem and modifiers. An
example would be: singular English words ending with -y, when pluralized, end with -ies.

a. Morphological Rules
b. Orthographic Rules
c. Parsing
d. None of the above

111. Types of stemming errors are:

a. under stemming
b. over stemming
c. Mid stemming
d. Both a and b

112. ____ is when two words with different stems are stemmed to the same root. This is also
known as a
_____.
a. Under Stemming, False Positive
b. Over Stemming, False Positive
c. Under Stemming, False Negative
d. Over Stemming, False Negative.

113. ______ is when two words that should be stemmed to the same root are not. This is also
known as
a____.
a. Under Stemming, False Positive
b. Over Stemming, False Positive
c. Under Stemming, False Negative
d. Over Stemming, False Negative.

114. It is possible to use backtracking in ____.

a. NFA
b. DFA
c. DAG
d. FA

115. It is not possible to use backtracking at all times in the case of _____.
a. NFA
b. DFA
c. DAG
d. FA
116. The full form of DFA is____.
a.Derived Finite Automata
Deterministic Final Automata
c. Deterministic Finite Automata
d. Duplicate Final Automation

117. The full form of NFA is ____.

a. Non-derived Finite Automata
b. Non-deterministic Final Automata
c. Non-deterministic Finite Automata
d. Non-Duplicate Final Automation

118. The generally accepted approach to morphological parsing is through the use of a _____,
which inputs words and outputs their stem and modifiers.
a. Non-deterministic Finite Automata(NFA)
b. Deterministic Finite Automata(DFA)
c. Directed Acyclic Graph(DAG)
d. Finite StateTransducer(FST)

119. FST as recognizer:

a. a machine that outputs pairs of strings of the language. Thus the output is a yes or no, and a
pair
of output strings.
b. A machine that reads a string and outputs another string.
c. a transducer that takes a pair of strings as input and output accept if the string-pair is
in the string-pair language, and a reject if it is not
d. A machine that computes relation between sets

120. FST as generator:

a. a machine that outputs pairs of strings of the language. Thus the output is a yes or no,
and a pair of output strings.
b. A machine that reads a string and outputs another string.
c. a transducer that takes a pair of strings as input and output accept if the string-pair is in
the
string-pair language, and a reject if it is not
d. A machine that computes relation between sets

121. FST as transducer:

a. a machine that outputs pairs of strings of the language. Thus the output is a yes or no, and a
pair
of output strings.
b. A machine that reads a string and outputs another string.
c. a transducer that takes a pair of strings as input and output accept if the string-pair is in
the
string-pair language, and a reject if it is not
d. A machine that computes relation between sets

2. FST as set relator:

a. a machine that outputs pairs of strings of the language. Thus the output is a yes or no, and a
pair
of output strings.
b. A machine that reads a string and outputs another string.
c. a transducer that takes a pair of strings as input and output accept if the string-pair is in
the
string-pair language, and a reject if it is not
d. A machine that computes relation between sets.

123. To construct a regular expression from a DFA, we replace each state in the ___one by
one with a
corresponding ___.
a. NFA, regular expression
b. DFA, regular expression
c. Regular expression, DFA
d. None of the above

124. If we can eliminate ________ from an FA, then our construction of an FA from a regular
expression can
be completed.
a. Epsilon transitions
b. States
c. DFA
d. NFA

125. In the fields of computational linguistics and probability, an_____ is a contiguous sequence
of n items from a given sample of text or speech. The items can be phonemes, syllables, letters,
words or base pairs according to the application.
a. corpus
b. Epsilon Transitions
c. N-grams
d. Lemma

126. Applications of n- gram:

a. design kernels that allow machine learning algorithms such as support vector machines to
learn from string data
b. find likely candidates for the correct spelling of a misspelled word
c. improve compression in compression algorithms where a small area of data requires n-grams
of greater length
d. All of the above

127. Syntactic n-grams are n-grams defined by paths in _________ dependency or constituent
trees rather than the linear structure of the text.
a. Syntactic

128. NLP is a subfield of ____________, computer science, and artificial intelligence concerned
with the
interactions between computers and human language
a. Definitions
b. Texts
c. Contexts
d. Linguistics

129. NLP does not involves in-

a. Speech recognition
b. Language understanding
c. Language generation
d. Computer vision

130. Which is the method of NLP

a. Neural
b. Statistical
c. Symbolic
d. All of the above

131. Which is not NLP task?

a. Discourse
b. Morphological analysis
c. Object recognition
d. Relational semantics

132. Which is the goal of NLP?

a. Content generation
b. Machine translation
c. Paraphrasing
d. All of the above

133. Where NLP is not used?

a. Chat bots
b. Image/Video captioning
c. Language translator
d. Predictive analysis

34. What input we can process with NLP?

a. Audio
b. Video
c. Text
d. All of the above

135. Which is not a level of NLP process?

a. Pragmatic
b. Discourse
c. Morphological
d. Textual

136. Which difficulty occurs in NLP?

a. Referential Ambiguity
b. Lexical Ambiguity
c. Contextual Ambiguity
d. Syntax level Ambiguity

137. Which is not application of NLP?

a. OCR
b. Sentiment analysis
c. Text classification
d. Auto-correct

138. How many steps of NLP is there?

a. 4
b. 5
c. 2
d. 6

139. ____________________ is the step in which an input sentence is converted into a hierarchical
structure
that corresponds to the units of meaning in the sentence.
a. Graph Processing
b. Syntactic Processing
c. Semantic Processing
d. All of the mentioned

140. Choose form the following areas where NLP can be useful.
a. Information Retrieval
b. Automatic Text Summarization
c. Automatic Question-Answering Systems
d. All of the mentioned

141. What is the main challenge/s of NLP?

a. Handling Ambiguity of Sentences
b. Handling Tokenization
c. Handling POS-Tagging
d. All of the mentioned

142. What is Machine Translation

a. Converts one human language to another
b. Converts human language to machine language
c. Converts any human language to English
d. Converts Machine language to human language

143. In linguistic morphology _____________ is the process for reducing inflected words to their
root form.
a. Rooting
b. Stemming
c. Text-Proofing
d. Both Rooting & Stemming

144. Which is not a step in NLP?

a. Lexical analysis
b. Syntactic analysis
c. Word analysis
d. Pragmatic Analysis

145. Which of the following is demerits of Top-Down Parser?

a. It is hard to implement.
b. Slow speed
c. inefficient
d. Both B and C

146. Given a sound clip of a person or people speaking, determine the textual
representation of the
speech.
a. Text-to-speech
b. Speech-to-text
c. Both A and B
d. None of the Above

147. Which of the following is used to mapping sentence plan into sentence structure?
a. Text planning

Sentence planning
c. Text Realization
d. None of the Above

148. Which is not a knowledge type of language processing?

a. Discourse
b. Pattern
c. Symbol
d. World

149. In morphology, we care about the ______ that make up the sentence
a. Characters
b. Words
c. Symbols
d. Lexicons

150. Which is not an example of morphology?

a. Prefix/suffix
b. Singularization/Pluralization
c. Lemmatization
d. Word detection

151. In parsing stage, we focus more on the _________ of the words within a sentence
a. Sequence
b. Group
c. Relationship
d. None of the above

152. Syntactical analysis is done at _______ level

a. Sentence
b. Word
c. Lexicon
d. Symbol

153. Morphological analysis is done at _____ level

a. Character
b. Lexicon
c. Word
d. Sentence