wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

FQuiz-NLP/NaiveBayes-AI

Total questions: 35

Worksheet time: 35mins

Name
Class
Date
1.

What does NLP stand for?

a)

Natural Language Processing

b)

Neural Language Processing

c)

Neural Language Programming

d)

Natural Learning Process

2.

Which of the following is a common application of NLP?

a)

Web hosting

b)

Spam filters

c)

Video editing

d)

Graphic design

3.

What is one of the challenges of language acquisition for computers?

a)

Complexity of unstructured data

b)

Lack of unstructured data

c)

Simplicity of human language

d)

Strict rules in language

4.

Which technique is used for sentiment analysis in NLP?

a)

Aspect extraction

b)

Text summarization

c)

Deep learning

d)

Named entity recognition

5.

What is the purpose of intelligent assistants like Siri and Alexa?

a)

To play music

b)

To identify speech patterns and infer meaning

c)

To send emails

d)

To manage calendars

6.

What does BERT stand for in NLP?

a)

Bidirectional Encoder Representations from Transformers

b)

Binary Encoding Representation Technique

c)

Basic Encoding for Real-time Translation

d)

Bidirectional Encoding for Real-time Text

7.

Which of the following is NOT a feature of NLP?

a)

Autocorrect

b)

Image processing

c)

Text summarization

d)

Voice recognition

8.

What is the main function of messaging filters in NLP?

a)

To enhance video quality

b)

To manage user accounts

c)

To identify unwanted messages

d)

To improve sound quality

9.

Which model is associated with Google AI for NLP?

a)

GPT-3

b)

BERT

c)

RoBERTa

d)

XLNet

10.

What is a common use of translation tools in NLP?

a)

To manage databases

b)

To edit videos

c)

To provide accurate translations

d)

To create graphics

11.

What does text analytics do?

a)

Generates audio from text

b)

Creates graphics from text

c)

Converts unstructured textual data into analyzable data

d)

Converts structured data into text

12.

What is the role of algorithms in NLP?

a)

To analyze the meaning and structure of words

b)

To create graphics

c)

To manage databases

d)

To enhance video quality

13.

What is one of the first applications of NLP?

a)

Spam filters

b)

Voice recognition

c)

Text summarization

d)

Data visualization

14.

Which of the following is a challenge for translation services?

a)

Strict rules in languages

b)

Direct translation of all languages

c)

Lack of data

d)

Different sentence constructions in languages

15.

What is the impact of BERT on search queries?

a)

It has no impact

b)

It improves understanding of complex searches

c)

It is used for video processing

d)

It only works with short queries

16.

What type of algorithm is Naive Bayes?

a)

Regression

b)

Clustering

c)

Classification

d)

Dimensionality Reduction

17.

Naive Bayes is based on which theorem?

a)

Bayes' Theorem

b)

Central Limit Theorem

c)

Pythagorean Theorem

d)

Law of Large Numbers

18.

In Naive Bayes, the term "naive" refers to:

a)

Ignorance of prior probabilities

b)

Simplification of dependent features

c)

Strong independence assumptions among features

d)

Use of simple math

19.

Bayes' theorem involves which of the following?

a)

Conditional probabilities

b)

Mean and variance

c)

Confidence intervals

d)

Decision trees

20.

What does Naive Bayes assume about input features?

a)

They are linearly dependent

b)

They are normally distributed

c)

They are conditionally independent

d)

They are binary

21.

Which of the following is NOT a variant of Naive Bayes?

a)

Gaussian Naive Bayes

b)

Multinomial Naive Bayes

c)

Bernoulli Naive Bayes

d)

Logistic Naive Bayes

22.

Which Naive Bayes variant is best for text classification with word counts?

a)

Gaussian

b)

Multinomial

c)

Bernoulli

d)

Logistic

23.

Bernoulli Naive Bayes is suitable for features that are:

a)

Continuous

b)

Ordinal

c)

Binary

d)

Categorical

24.

Gaussian Naive Bayes is used when the features are:

a)

Binary

b)

Discrete

c)

Count-based

d)

Continuous and normally distributed

25.

In Naive Bayes, what does the prior probability P(C) represent?

a)

Likelihood of the data

b)

Probability of the class before observing features

c)

Probability of the features

d)

Conditional probability of class given features

26.

What is the primary advantage of Naive Bayes?

a)

High accuracy

b)

Handles missing values natively

c)

Fast training and prediction

d)

Works well with multicollinearity

27.

Which metric is commonly used to evaluate Naive Bayes performance?

a)

Mean Squared Error

b)

R-squared

c)

Accuracy

d)

Adjusted R-squared

28.

A drawback of Naive Bayes is that it:

a)

Works only on binary classification

b)

Is computationally expensive

c)

Assumes feature independence, which is rarely true

d)

Needs large amounts of training data

29.

Naive Bayes is considered a generative model because:

a)

It models P(y|x) directly

b)

It models the decision boundary

c)

It models how data is generated by estimating P(x|y)

d)

It does not use probability distributions

30.

Laplace smoothing is used in Naive Bayes to:

a)

Normalize the data

b)

Prevent zero probability for unseen features

c)

Increase model accuracy

d)

Ensure Gaussian distribution

31.

Which of the following is NOT true about Naive Bayes?

a)

It can be used for spam detection

b)

It works well with high-dimensional data

c)

It performs poorly with correlated features

d)

It always gives the most accurate results

32.

The likelihood term in Bayes' theorem for Naive Bayes is:

a)

P(C)

b)

P(X|C)

c)

P(C|X)

d)

P(X)

33.

In text classification, which Naive Bayes model is generally preferred?

a)

Gaussian

b)

Multinomial

c)

Bernoulli

d)

Both B and C depending on feature format

34.

Which preprocessing step is crucial for Naive Bayes in NLP tasks?

a)

Feature scaling

b)

Removing outliers

c)

Tokenization and vectorization

d)

Dimensionality reduction

35.

Naive Bayes classifiers are particularly suitable when:

a)

Features are dependent

b)

Dataset has many categorical features

c)

You need a non-probabilistic model

d)

Data is highly imbalanced