MS_NLP WORKSHEET
MS_NLP WORKSHEET
MS_NLP WORKSHEET
Correct
Question Choice 1 Choice 2 Choice 3 Choice 4
Answer
Natural Neural Natural Network Natural
What does NLP
Language Language Linguistic Language Language
stand for?
Processing Processing Programming Processing Processing
Which field does
Artificial Artificial
NLP primarily Physics Biology Mathematics
Intelligence Intelligence
belong to?
What is a common Image Speech Data Network Speech
task in NLP? recognition recognition encryption security recognition
Which of the
following is a
TensorFlow NumPy NLTK Pandas NLTK
popular NLP
library?
What is Analyzing
Dividing text into Dividing text Converting text Dividing text
tokenization in sentence
sentences into words to speech into words
NLP? structure
Which model is
commonly used for
CNN RNN SVM KNN RNN
language
generation?
Understanding Analyzing Analyzing
What is sentiment Translating Summarizing
customer emotions in emotions in
analysis? languages documents
behavior text text
Which technique is
Supervised Reinforcement Supervised
often used for text Clustering Regression
learning learning learning
classification?
What is a common Weather Fraud
Chatbots Image editing Chatbots
application of NLP? forecasting detection
What does Converting Converting
Removing Counting word Creating n-
'lemmatization' words to their words to their
punctuation frequency grams
refer to in NLP? base form base form
Correct
Question Choice 1 Choice 2 Choice 3 Choice 4
Answer
What is automatic Reducing Enhancing Reducing
Creating new Improving
summarization information graphic information
content writing skills
primarily used for? overload design overload
How does By identifying By increasing By identifying
By generating By creating
sentiment analysis customer website customer
more content advertisements
help companies? opinions traffic opinions
Which of the
following is an Social media Image Voice
Spam filtering Spam filtering
application of text monitoring recognition commands
classification?
Why is It aids in It aids in
It helps in It increases
understanding understanding It boosts understanding
identifying social media
sentiment in purchasing website SEO purchasing
spam followers
context important? decisions decisions
Which virtual
assistant is known
Google Google
for making calls Photoshop Microsoft Word Excel
Assistant Assistant
and sending
messages?
What does
Redundancy Redundancy
automatic Loss of original Complex Excessive
from multiple from multiple
summarization help meaning language data usage
sources sources
avoid?
What type of data
can sentiment Financial Social media Technical Weather Social media
analysis be reports posts manuals forecasts posts
conducted on?
Which of the
following is NOT a Managing Debugging Setting Debugging
Playing music
function of virtual schedules software reminders software
assistants?
What is one benefit
Improves Organizes Creates new Enhances Organizes
of text
grammar information content visual appeal information
classification?
What is the main
challenge
Information User Information
addressed by Data analysis Content creation
overload engagement overload
automatic
summarization?
Correct
Question Choice 1 Choice 2 Choice 3 Choice 4
Answer
A bot that A bot that
A bot that
What is a script- follows a A highly A bot with wide follows a
learns with
bot? programmed flexible bot functionality programmed
data
script script
Which type of bot
Smart-bot Script-bot Both types Neither type Smart-bot
requires coding?
What is a Ability to
Limited No learning Ability to learn
characteristic of learn from Easy to create
functionality capability from data
smart-bots? data
Which of the
following is an Google Customer care Customer care
Siri Alexa
example of a script- Assistant chatbots chatbots
bot?
What type of
Small Larger Larger
database do smart- No databases Only text files
databases databases databases
bots work with?
Which of the
following is NOT a Easy Limited Learning from Programmed Learning from
feature of script- integration functionality data responses data
bots?
What is a key
Humans
difference between Computers can Humans use Computers Humans
process
human and learn from only spoken understand process sounds
sounds
computer conversation language emotions continuously
continuously
language?
They can They have They can
What makes smart- They follow They require
perform a limited perform a
bots powerful? strict scripts no coding
variety of tasks functionality variety of tasks
Which of the
A bot that A bot with
following is A basic FAQ
connects users Siri scripted Siri
considered a bot
to humans responses
smart-bot?
Language Language
What is a limitation Learning High
Flexibility processing processing
of script-bots? capabilities functionality
skills skills
Correct
Question Choice 1 Choice 2 Choice 3 Choice 4
Answer
Through Through
How does the human Using only the By visual Directly from
eardrum and eardrum and
brain process sound? ears interpretation the mouth
neurons neurons
What does syntax refer Meaning of Grammatical Pronunciation Vocabulary Grammatical
to in human language? words structure rules size structure
What is the primary
language of Words Numbers Symbols Sounds Numbers
computers?
What happens if there
is a mistake in It processes It ignores the It throws an It asks for It throws an
computer language anyway mistake error clarification error
input?
Which of the following
is NOT a part of human Nouns Verbs Adverbs Binary code Binary code
language structure?
How does the brain
By volume By interest By clarity By frequency By interest
prioritize sounds?
Which of the following
Basic and Complex and Restricted to Complex and
describes human Error-prone
simple adaptable numbers adaptable
language?
What do humans ask
for when they don't
Correction Clarity Repetition Explanation Clarity
understand a
message?
Which element is
Context Syntax Semantics Numbers Numbers
essential for computer
language
understanding?
What is one major
Computers Computers
difference between Humans use Humans speak Computers
require require
human and computer nouns faster make errors
numbers numbers
languages?
Correct
Question Choice 1 Choice 2 Choice 3 Choice 4
Answer
What does the word
Political All of the
'red' illustrate in Color Emotion All of the above
affiliation above
context?
What is the
importance of It makes
It changes It alters It simplifies It alters
context in sentences
syntax meaning language meaning
understanding longer
language?
A A
What does 'perfect A syntactically An
grammatically An emotional grammatically
syntax, no meaning' incorrect ambiguous
correct sentence correct
refer to? sentence sentence
sentence sentence
What is the first
step in converting Text Machine Speech Text
Data analysis
language to normalization learning recognition normalization
numbers?
Why is natural
It has too many It contains It uses It has too many
language complex It is too simple
rules emotions numbers rules
for computers?
Cleaning and Translating text Cleaning and
What is text Creating new Complicating
simplifying text to another simplifying text
normalization? text data existing text
data language data
How does text
normalization aid in By making data By reducing By increasing By eliminating By reducing
language more complex ambiguity creativity all text ambiguity
processing?
Which of the
following is NOT a Removing Converting to Adding new Removing stop Adding new
step in text punctuation lowercase words words words
normalization?
Natural Numerical Natural Network Natural
What does NLP
Language Language Linguistic Language Language
stand for?
Processing Programming Patterns Protocol Processing
What is a key
challenge for Complex Complex
Too many Standardized
machines in Lack of data meanings and meanings and
speakers grammar rules
understanding contexts contexts
human languages?
Correct
Question Choice 1 Choice 2 Choice 3 Choice 4
Answer
What is the first step
Removing Sentence Data Sentence
in Text Tokenisation
Stopwords Segmentation Collection Segmentation
Normalisation?
What does Removing Dividing Dividing
Translating Summarising
tokenisation special sentences sentences into
text sentences
involve? characters into words words
Frequent but Frequent but
What are Important Special Punctuation
contextless contextless
stopwords? keywords characters marks
words words
To focus on To focus on
Why do we remove To shorten To translate To make it
meaningful meaningful
stopwords? the text the text readable
terms terms
A word,
A word, number,
A complete number, or Only nouns in A type of
What is a token? or special
sentence special a sentence punctuation
character
character
What might be
Single Multiple Multiple
included in a Only numbers Just stopwords
sentences documents documents
corpus?
What is the purpose To divide the To divide the
To remove To summarize To tokenize
of sentence corpus into corpus into
stopwords the text the text
segmentation? sentences sentences
Which of the
following is NOT a Data Removing Sentence
Tokenisation Data Annotation
step in Text Annotation Stopwords Segmentation
Normalisation?
When might you
It depends on
keep special Only in It depends on
Always the corpus Never
characters in a numbers the corpus type
type
corpus?
What do we call the
whole textual data
Token Segment Corpus Sentence Corpus
from multiple
documents?
Correct
Question Choice 1 Choice 2 Choice 3 Choice 4
Answer
What is the
To treat same To treat same
purpose of To increase the To ensure case To remove
words as words as
converting text to text length sensitivity punctuation
identical identical
lower case?
It removes It removes
What does It converts affixes and It converts all It ensures all affixes and
stemming do to words to their reduces words words to words are reduces words
words? synonyms to their root uppercase meaningful to their root
forms forms
Which of the
following is a key Lemmatization Stemming Lemmatization
Stemming is Both
difference results in checks for results in
slower than processes are
between meaningful word meaningful
lemmatization the same
stemming and words meanings words
lemmatization?
What is an
example of a
Studies to
word that might Healed to heal Healing to heal Healer to heal Studies to studi
studi
be stemmed
incorrectly?
What does
It retains all
lemmatization It is always the It is a It has no It is a
original
ensure about the shortest form meaningful word affixes meaningful word
meanings
resulting word?
What is the Bag
Converting Generating Converting
of Words model Stemming and Removing
words to synonyms for words to
primarily used lemmatization stop words
numbers words numbers
for?
Which process is Text
Lemmatization Bag of Words Stemming Stemming
generally faster? normalization
In text
normalization, To enhance
To maintain To reduce noise To increase To reduce noise
why are case
word meaning in data text length in data
stopwords sensitivity
removed?
Which of the
following is NOT a Maintains Prevents
Reduces data Helps in feature Maintains case
benefit of using case duplication of
complexity extraction sensitivity
lower case sensitivity words
conversion?
What is the first
Lower case Lower case
step in text Lemmatization Stemming Bag of Words
conversion conversion
normalization?
Correct
Question Choice 1 Choice 2 Choice 3 Choice 4
Answer
What does the
Unique words Word Unique words
Bag of Words Sentences in Document
and their meanings and and their
model primarily order summaries
frequencies synonyms frequencies
provide?
What is the first
step in Create
Create Text Remove stop Text
implementing the document
Dictionary Normalisation words Normalisation
Bag of Words vectors
algorithm?
Words that Words that
Rare words that Words that
What are stop occur Words that are occur frequently
add significant are specific to
words? frequently and only nouns and add little
value a subject
add little value value
How are By finding By
By counting By finding word
document vectors By analyzing the word summarizing
the number of frequencies in
created in the Bag order of words frequencies in document
unique words documents
of Words model? documents content
Term Textual
Total Frequency Term Term Frequency
Frequency Frequency
What does TFIDF in Document Frequency and and Inverse
and Inverse and Inverse
stand for? Indexing Document Document
Document Data
Framework Importance Frequency
Frequency Frequency
They convey
Why are frequent They convey the
the main They are always They are the They appear
words important in main subject of
subject of the stop words least valuable only once
a corpus? the document
document
What happens to
the value of rare It decreases It increases with It remains It is always It increases with
words in a with frequency rarity constant negligible rarity
corpus?
What type of
words are typically
Frequent Subject-
removed during Stop words Rare words Stop words
words specific words
text
normalization?
What aspect does
Word Word Document
the Bag of Words Word order Word order
frequency uniqueness count
model ignore?
Which of the
following best A sequence- A frequency- A grammar- A meaning- A frequency-
describes the Bag based model based model based model based model based model
of Words model?
Correct
Question Choice 1 Choice 2 Choice 3 Choice 4
Answer
Importance of
What does Frequency of a Frequency of a Commonness of Frequency of a
a word in
term frequency word in one word across all a word in a word in one
natural
measure? document documents corpus document
language
What is Number of times Number of Number of
Total words in Total number of
document a word appears documents that documents that
a document documents
frequency? in a document contain a word contain a word
How is TFIDF TF(W) + TF(W) * log(TF(W) * TF(W) *
TF(W) - IDF(W)
calculated? log(IDF(W)) log(IDF(W)) IDF(W)) log(IDF(W))
High term Low term High term
What indicates High
frequency and frequency and Low frequency frequency and
a high TFIDF frequency in
low document high document in all documents low document
value? all documents
frequency frequency frequency
Which
application Document Information Sentiment Sentiment
Topic modeling
does TFIDF classification retrieval analysis analysis
NOT support?