1 Which among the following is one of the stages in NLP pipeline?

a) Sentiment Analysis

b) Tokenization

c) Spell Checking

d) Syntax Analysis

2 ____________ POS tagger uses probabilities.

a) Rule based

b) Stochastic

c) Procedure based

d) Object based

3 _________ Is The Type Of Morphology That Changes The Word Category And Affects The Meaning.

a) Inflectional

b) Derivational

c) Cliticization

d) Text-Proofing

4 How is the word "changing" lematized?

a) chang

b) changin

c) chan

d) change

5 Which of the following is used to map sentence plan into sentence structure?

a) Text planning

b) Sentence planning

c) Text Realization

d) Text Summarization

6 Which of the following techniques is most appropriate to get root of word without considering word syntax

a) Stemming

b) Lemmatization

c) Stop word removal

d) Rooting

7 The car hit the pole while it was moving." What type of ambiguity exists in the above sentence?
 a) Lexical

b) Syntactic

c) Referential

d) Pragmatic

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

a) Value, Label, Markov

b) Word, Tag, Bayes

c) Attribute, Variable, Bayes

d) Input, Label, Markov

9 "It is the inverse probability of the test data which is normalized by the number of words." This is the
definition of

a) Language Model

b) N-gram

c) Perplexity

d) Laplace smoothing

10 How many bi-grams can be generated from given sentence: “Analytics Vidhya is a great source to learn
data science”

a) 7

b) 8
c) 9

d) 10

Choose form the following areas where NLP can be useful.

a) Automatic Text Summarization
b) Automatic Question-Answering Systems
c) Information Retrieval
d) All of the mentioned

Many words have more than one meaning; we have to select the meaning which makes the most sense in
context. This can be resolved by
a) Fuzzy Logic
b) Word Sense Disambiguation
c) Shallow Semantic Analysis
d) All of the mentioned

One of the main challenge/s of NLP Is _____________

a) Handling Ambiguity of Sentences
b) Handling Tokenization
c) Handling POS-Tagging
d) All of the mentioned
 ___________ represents the knowledge about linguistic sounds

a) b) Morphology Phonology

c) Pragmatics

d) Discourse

Which resolve tagging _____________ambiguities by using a training corpus?

a) Brill tagger

b) HMM tagger

c) Stochastic tagger

d) Rule based tagger

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

Adding one to all bigrams is followed in which of the following smoothing types

a) Knesser-Ney Smoothing

b) Laplace Smoothing

c) Intrinsic

d) Extrinsic

The model that includes frequency or probability belongs to which type of POS tagging

a) Rule based

b) Stochastic

c) Transformation based

d) All of the above

N-grams are defined as the combination of N keywords together. How many bi-grams can be generated from
the given sentence: Gandhiji is the father of our nation

a) 7

b) 6

c) 8
d) 9

The main morpheme of the word is called

a) Affix
b) Prefix

c) Stem
d) Circumfix
1 One of the main challenge/s of NLP?
a) Handling Ambiguity of Sentences
b) Handling Tokenization
c) Handling POS-Tagging
d) All of the mentioned
2 In linguistic morphology, _____________ is the process for reducing inflected words to their root
form.
a) Stemming
b) Rooting
c) Text Proofing
d) Both a & b
3 Which among the following is not an application of natural language programming (NLP)?
a) Chatbox
b) Speech recognition
c) Sentimental analysis
d) Market Basket Analysis
4 Pick the lemmatization actions
a) was, am, are, is → be
b) study, studying, studied → study
c) troubled, troubling, trouble → trouble
d) has have, had → have
5 In the sentence, “They bought a blue house”, the underlined part is an example of _____.
a. Noun phrase
b. Verb phrase
c. Prepositional phrase
d. Adverbial phrase

6 What type of ambiguity exists in the word sequence “Time flies”?

(a) Syntactic
(b) Semantic
(c) Phonological
(d) Anaphoric
7 Knowledge of the relationship of meaning to the goals and intentions of the speaker is ________

a) Morphology
b) Semantics
c) Pragmatics
d) Discourse
8 The act of converting a text document into a set of individual words is referred as ______ .
a) Tokenization
b) Stemming
c) Lemmatization
d) All of the above
 Which of the text parsing techniques can be used for noun phrase detection, verb phrase detection,
9 subject detection, and object detection in NLP.

a) Continuous Bag of Words

b) Skip Gram and N-Gram extraction
c) Part of speech tagging
d) Dependency Parsing and Constituency parsing

10 N- gram Language model cannot be used for

a) Spelling Correction
b) Predicting the completion of a sentence
c) Removing semantic ambiguity
d) Speech Recognition
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 In linguistic morphology, _____________ is the process for reducing inflected words to their root
form.
a. Stemming
b. Rooting
c. Text Proofing
d. Both a & b
3 What is the main challenge of NLP?
a. Handling POS-Tagging
b. Handling Tokenization
c. Handling Ambiguity of Sentences
d. None of the above
4 What are the input and output of an NLP system?
a. Speech and noise
b. Noise and Written Text
c. Noise and value
d. Speech and Written Text
5 “He lifted the beetle with red cap”. Identify type of ambiguity
a. Lexical ambiguity
b. Referential ambiguity
c. None of the Above
d. Syntax Level ambiguity
6 Parts-of-Speech tagging determines ___________
a. part-of-speech for each word dynamically as per meaning of the sentence
b. part-of-speech for each word dynamically as per sentence structure
c. all part-of-speech for a specific word given as input
d. All of the above
7 Natural language processing is divided into the two subfields of -
a. symbolic and numeric
b. algorithmic and heuristic
c. time and motion
understanding and generation
8 Which of the following techniques can be used to compute the distance between two word vectors in
NLP?
a. Lemmatization
b. Cosine Similarity
c. N-grams
d. Euclidean distance
9 How many steps of NLP is there?
a. 3
b. 4
 c. 5
d. 6
10 Who is the father of NLP?
a. Enjamin Bandler
b. Richard Bandler
c. Elijah Bandler
None of these
1 Many Words have more than one meaning; we have to select the meaning which makes the most
sense in context. This can be resolved by ______.
a) Fzzy Logic b)Shallow Semantic Analysis
c)Word Sense Disambiguationd) All of the above
2 Parts-of-Speech tagging determines _____
a) part-of-speech for each word dynamically as per meaning of the sentence
b) part-of-speech for each word dynamically as per sentence structure
c) all part-of-speech for a specific word given as input
d) All of the above
3 Which of the text parsing techniques can be used for noun phrase detection, verb phrase detection,
Subject detection and object detection in NLP?
a) Continuous Bag of Words
b)Skip Gram and N-Gram extraction
c) Parts of Speech tagging
d) Dependency Parsing and Constituency Parsing
4 ______ is the step in which an input sentence is converted into a hierarchical structure that
corresponds to the unit of meaning in the sentence.
a) Syntactic Processing b) Semantic Processing
c) Graph Processing d) All of the above
5 Which of the following approach is not used for meaning representation?
a) Case Grammar b)First Order Predicate Logic
c) POS tagging d) Semantic Nets
6 _________ has the same spelling but different and related meaning.
a) Hyponymy b)Homonymy c) Polysemy d) Meronymy
7 Reciprocal semantic relationship between pairs of words is known as _________.
a) Meronymy b) Converseness c) Polysemy d) Hyponymy
8 ________ is a semantic generalization over the specific roles that occur with specific verbs.
a) Thematic Roles b) POS tag c) Frame d) None of the above
9 Which of the following uses verb specific semantic roles
a) Framenets b) POS Tags c) Propbank d) None
10 In the sentence “my mother is listening to music”, she is getting the role of ________
a) Agent b) Theme c) Experiencer d) Subject
1 ___________ can also specify the results of processes described by utterances in a discourse.

a) Pronouns
b) demonstratives
c) generics
d) inferrables

2 Identify the Class of methods that induces a classifier from manually sense-tagged text using machine learning
techniques.
a) Supervised WSD
b) unsupervised WSD
c) Semi-supervised WSD
d) Normal WSD

3 Identify 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
 4 Choose the type of analysis, in which linear sequence of words are transformed into structure that show how
the words are related to each other is the part of _____ Analysis.
a) Semantic
b) Syntactic
c) Lexical
d) Pragmatic

5 Analyse the following techniques and choose which is used to remove semantic ambiguity?
a) Fuzzy Logic
b) Shallow Semantic Analysis
c) Syntactic analysis
d) Word Sense Disambiguation
6 Identify the Type Of Ambiguity Does Sentence Have
"I Saw The Boy With A Pony Tail "
a) Semantic Ambiguity
b) Pragmetic Ambiguity
c) Structured Ambiguity
d) Simplex
7 List the components, that Ontology is composed of
a) terms and classes
b) terms and objects
c) objects and classes
d) terms and relationships
8 What is Coreference Resolution?
a) Anaphora Resolution
b) Given a sentence or larger chunk of text, determine which words (“mentions”) refer to the
same objects (“entities”)
c) Converts one human language to another
d) Does Discourse Analysis
9 Select the correct option, Given a sentence or larger chunk of text, determine which words (“mentions”) refer
to the same objects (“entities”)
a) Anaphora Resolution
b) Coreference Resolution
c) Noun Resolution
d) Pronoun Resolution
10 Analyse the Web context, and select the role of ontologies, which provides
a) comparative understanding of domain
b) competitive understanding of domain
c) shared understanding of domain
d) preferred understanding of domain
1 The english words through and threw are examples of____________
a. Automymy
b. Polysemy
c. Synonymy
d. Homophony

2 Given a sentence or larger chunk of text, determine which words (“mentions”) refer to the same objects
(“entities”)
a. Anaphora Resolution
b. Coreference Resolution
c. Noun Resolution
d. Pronoun Resolution
3 WordNet is the _______________ database
a. Symbol
b. Word
c. Lexical
d. Annotation
4 Beverage = coffee - tea - shake, is example of ______
a. Meronymy
 b. Hyponymy
c. Polysemy
d. Clines
5 Which of the following technique is used to remove semantic ambiguity?
a. Fuzzy Logic
b. Shallow Semantic Analysis
c. Syntactic analysis
d. Word Sense Disambiguation
6 The entity that is involved in or affected by the action, or that is simply being described (The boy kicked --
> the ball.) (-->The ball was red.)
a. denotation
b. semantic features
c. homophones
d. theme ("patient")
7 The entity that performs the action; can be human or non-human (-->The boy kicked the ball.)
a. agent
b. source
c. instrument
d. hyponym

8 Which data is used to use supervised approach for Machine translation

a. Plain text
b. Labelled text
c. Dictionary
d. Vectors
9 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
10 Discourse Analysis Involves The Study Of Relationship Between?
a. Programming Language And Contextual Foreground
b. Language And Dictionary Background
c. Dictionary And Knowledge
d. Language And Contextual Background
1 In information retrieval, extremely common words which would appear to be of little value in helping document
selection that are to be excluded from the index vocabulary are called ____.
a) Stop word b) Tokens c) Lemmatized Words d) Stemmed Words

2 Which of the following transforms unstructured information in a corpus of documents or web pages into a
structured database?
a) Summarization b) Information Retrieval
c) Information Extraction d) Information Fusion
3 A metric used to measure the importance of a term in a text document collection is called _____.
a) Document Frequency b) Term Frequency
c) Inverse Term Frequency d) Inverse Document Frequency
4 In _________ IR model, the documents are ranked by the cosine of the angle between the document vectors and
the query vector.
a) Boolean Model b) Vector Space Model
c) Probabilistic Model d) Fuzzy Model
5 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
6 The similarity measure which considers only the magnitudes of the vectors is _____.
a) Euclidean Distance b) Dot Product c) Cosine Similarity d) None
7 Which among the below method preserve the syntactic and semantic information?
a) Word Embedding b) CountVectorizer c) TF-IDF d) BOW
 8 How many gates the LSTM have?
a) 5 b) 4 c) 3 d) 2
9 Which of the following is not the job of Word Embedding?
a) Labeling b) Capturing the Contextual Meaning
c) Reduce the Dimensionality d) Finding the words around
10 _____ is not a Probabilistic NLP model.
a) Rule Based Model b) Regression Model
c) Markov Model d)All of the above
1 Trains two independent LSTM language model left to right and right to left and
shallowly concatenates them.
a) GPT
b) BERT
c) ULMFit
d) ELMo

2 In this technique, content is extracted from the original data, but the extracted content is
not modified in any way
a) Extraction-based summarization
b) Abstraction-based summarization
c) Aided summarization
d) Key phrase extraction
3 The standard approach to information retrieval system evaluation involves around
the notion of
a) Quantity of documents in the collection
b) Relevant and non-relevant documents.
c) Accuracy
d) User happiness
4 Which of the following includes major tasks of NLP?
a) Automatic Summarization
b) Discourse Analysis
c) Machine Translation
d) Automatic Summarization & Discourse Analysis & Machine Translation
5 In NLP, Context modeling is supported with which one of the following word
embeddings
a) Word2Vec
b) GloVe
c) BERT
d) ELMo
6 Which data is used to use supervised approach for Machine translation
a) Plain text
b) Labeled text
c) Dictionary
d) Vectors
7 Bag of Words in text preprocessing is a
a) Feature scaling technique
b) Feature extraction technique
c) Feature selection technique
d) Feature abstraction technique
8 Which application use to determine people in context?
a) Stemming
b) Lemmatization
 c) Stop word removal
d) Named entity recognition
9 Which of the following measurements are used to evaluate the quality of entity
recognition?
a) Precision
b) Recall
c) F-measure
d) All of the above

10 A bag of words model uses

a) A vocabulary of known words and A measure of the presence of known words
b) A vocabulary of text and sentences
c) A vocabulary of meaningful sentences
d) A measure of text and sentences
1 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

2 The standard approach to information retrieval system evaluation involves around the notion of:
a. Quantity of documents in the collection
b. Relevant and non relevant documents.
c. Accuracy
d. user happiness
3 Deciding Insurance premium of a car based on online customers reviews is an application of
______________________.
a. Information Retrieval
b. Information Extraction
c. Sentiment Analysis
d. Text Summarization
4 Which Application of NLP is concerned with intendent Documents Relevant to a user's Query?
a. Speech Recognition
b. Natural Language Interfaces To Db
c. Information Extraction
d. Information Retrieval
5 Google Translate is one of the ________________ application.
a. Machine translation
b. Information Retrieval
c. Information Extraction
d. Summarisation
6 Classifying email as a spam, labelling WebPages based on their content, voice recognition are the example
of _____.
a. Supervised learning
b. Unsupervised learning
c. Machine learning
d. Deep learning
7 Trains two independent LSTM language model left to right and right to left and shallowly concatenates
them
a. GPT
b. BERT
c. ULMFit
d. ELMo
8 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
9 Which Algorithm Is Used For Solving Temporal Probabilistic Reasoning?
a. Hidden Markov Model
b. Breadth-First Search
c. Hill-Climbing Search
d. Depth-First Search
10 To find relevance of word in a document technique used
a. TF-IDF
b. Lemma
c. Tokenizer
d. Pos tagging