wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

NLP Multiple Choice Questions (Part 1)

Total questions: 150

Worksheet time: 1hrs 15mins

Name
Class
Date
1.

What is the primary purpose of Natural Language Processing (NLP)?

a)

To enable computers to understand, analyze, and process human languages.

b)

To generate binary code for machine execution.

c)

To analyze the grammar of computer programming languages.

d)

To convert numerical data into visual representations.

2.

Which of the following is NOT a feature of natural languages?

a)

They are static and do not change over time.

b)

They are redundant.

c)

Governed by rules like syntax and lexicon.

d)

Information can be conveyed in multiple ways.

3.

Which NLP application is used to generate captions for video content in real-time?

a)

Language Translation

b)

Sentiment Analysis

c)

Text Classification

d)

Autogenerated Captions

4.

Which stage of NLP is responsible for checking the grammar and structural correctness of sentences?

a)

Pragmatic Analysis

b)

Syntactic Analysis

c)

Lexical Analysis

d)

Semantic Analysis

5.

What is the main task of Semantic Analysis in NLP?

a)

Analyzing the relationship between successive sentences.

b)

Assessing the meaningfulness of the input text.

c)

Checking the grammar of the sentences.

d)

Dividing text into sentences and words.

6.

The term "pulling your leg" is a good example for which stage of NLP?

a)

Syntactic Analysis

b)

Pragmatic Analysis

c)

Lexical Analysis

d)

Semantic Analysis

7.

What is a "corpus" in the context of text processing?

a)

A single document.

b)

A special character in a sentence.

c)

A collection of written text from multiple documents.

d)

A word that has been stemmed.

8.

The process of dividing sentences into words, numbers, and special characters is called:

a)

Segmentation

b)

Tokenization

c)

Normalization

d)

Stemming

9.

Which of the following is a key characteristic of "stop words"?

a)

They are frequently occurring words that do not add significant value.

b)

They are always meaningful and essential for context.

c)

They have the lowest occurrence in the text.

d)

They add the most value to the corpus.

10.

What is the difference between stemming and lemmatization?

a)

Stemming is slower than lemmatization.

b)

Stemming produces a meaningful root word, while lemmatization does not.

c)

Stemming removes affixes, and the resulting word may not be meaningful, while lemmatization ensures the root word is meaningful.

d)

They are the same process with different names.

11.

In the Bag of Words model, what does the "bag" symbolize?

a)

That the unique words are stored in a bag-like structure.

b)

That the sequence of sentences is preserved.

c)

That only the most important words are kept.

d)

That the sequence of words or tokens does not matter.

12.

What does TFIDF stand for?

a)

Term Frequency-Inverse Document Frequency

b)

Term Frequency-Integrated Document Function

c)

Text Feature-Inverse Document Frequency

d)

Total Frequency-In-Document Function

13.

Which of the following is a TFIDF application?

a)

Document Classification

b)

Chatbot Development

c)

Image Recognition

d)

Voice Synthesis

14.

Which of the following tools is a "no-code" NLP tool mentioned in the document?

a)

Python

b)

NLTK

c)

SpaCy

d)

MonkeyLearn

15.

What is a chatbot?

a)

A program that generates random sentences.

b)

A computer program that simulates human conversation.

c)

A tool used to extract keywords from text.

d)

A type of database for storing textual data.

16.

Which of the following is a primary function of a chatbot in an e-commerce site?

a)

To perform mathematical calculations.

b)

To generate sales leads and increase sales.

c)

To translate the website into different languages.

d)

To write code for the website.

17.

The conversion of a word like "healed" to its base form "heal" is an example of which text processing technique?

a)

Tokenization

b)

Lemmatization or Stemming

18.

What is the key concept illustrated by the sentence "His face turned red after he found out that he took the wrong bag"?

a)

The importance of grammar.

b)

The process of stemming.

c)

The significance of context in understanding meaning.

d)

The need for tokenization.

19.

Which tool is a Python library for text processing?

a)

MonkeyLearn

b)

NLTK

c)

Cleverbot

d)

Orange Data Mining

20.

In the TFIDF calculation, what does a low Inverse Document Frequency (IDF) value indicate for a word?

a)

The word is rare and valuable.

b)

The word is a stop word and has a negligible value.

c)

The word is essential for document classification.

d)

The word has a high term frequency in one document.

21.

What is the core idea of a Bag of Words model?

a)

Representing text as a collection of words, disregarding their order.

b)

Preserving the grammatical structure of sentences.

c)

Counting the number of unique words in a document.

d)

Creating a document vector for each document.

22.

What does the term "lexicon" refer to in the context of NLP?

a)

A set of grammatical rules.

b)

The output of the semantic analysis stage.

c)

The process of dividing text into paragraphs.

d)

A collection of various words and phrases used in a language.

23.

Which step of text normalization ensures that "Hello," "hello," and "HELLO" are treated as the same word?

a)

Converting text to a common case

b)

Tokenization

c)

Stop word removal

d)

Stemming

24.

What is the relationship between Discourse Integration and preceding/succeeding sentences?

a)

It removes unnecessary words from them.

b)

It forms a relationship between them to create a coherent story.

c)

It segments them.

d)

It converts them to a common case.

25.

According to the document, what is the primary challenge for computers in understanding human language?

a)

Human languages are too simple.

b)

Human languages are complex and require simplification.

c)

Computers can only process visual data.

d)

Computers lack the necessary programs.

26.

A word with a high TFIDF value is likely to have:

a)

Low term frequency and high document frequency.

b)

High term frequency and high document frequency.

c)

Low term frequency and low document frequency.

d)

High term frequency and low document frequency.

27.

What is the process of normalizing text to a lower level called?

a)

Text Summarization

b)

Text Normalization

c)

Text Categorization

d)

Text Simplification

28.

A document vector is created in which step of the Bag of Words algorithm?

a)

TFIDF calculation

b)

Creating document vectors

c)

Creating a Dictionary

d)

Text Processing

29.

What is the primary function of keyword extraction?

a)

To translate a text into different languages.

b)

To classify a document into a category.

c)

To automatically identify and extract the most important words or phrases from a text.

d)

To check the grammatical structure of a sentence.

30.

What is the main goal of text normalization?

a)

To make text visually appealing.

b)

To prepare textual data for machine learning.

c)

To translate text to another language.

d)

To make text more complex.

31.

Which NLP stage focuses on the practical and logical relevance of a sentence in the real world?

a)

Semantic Analysis

b)

Lexical Analysis

c)

Syntactic Analysis

d)

Pragmatic Analysis

32.

What is the first step in the Natural Language Processing (NLP) process?

a)

Syntactic Analysis

b)

Semantic Analysis

c)

Lexical Analysis

d)

Pragmatic Analysis

33.

Which of the following is a benefit of using a chatbot on an e-commerce site?

a)

It can only handle simple, scripted conversations.

b)

It can analyze visual data.

c)

It can process numerical data.

d)

It can generate sales leads.

34.

What is the main idea behind a "Bag of Words" model?

a)

It only works for very short sentences.

b)

It counts the frequency of words while ignoring their sequence.

c)

It is a model for translating languages.

d)

It focuses on the grammatical relationships between words.

35.

What is the main purpose of the Inverse Document Frequency (IDF) component in TFIDF?

a)

To measure the frequency of a word in a single document.

b)

To reduce words to their root form.

c)

To classify documents into categories.

d)

To assess the importance of a word by penalizing words that appear frequently across many documents.

36.

Which of the following statements about TFIDF is correct?

a)

The TFIDF value is not related to TF or DF.

b)

Words with low TF and high DF have a high TFIDF value.

c)

Words with high TF and high DF have a high TFIDF value.

d)

Words with high TF and low DF have a high TFIDF value.

37.

What is a "lemma" in the context of lemmatization?

a)

A word that is a stop word.

b)

A word with no meaning.

c)

A word that has not been normalized.

d)

A meaningful word that is the root of another word.

38.

What is the primary difference between a "script-bot" and a "smart-bot"?

a)

There is no difference; the terms are interchangeable.

b)

Script-bots have a limited, pre-defined set of responses, while smart-bots can learn and interact more dynamically.

c)

Script-bots are used for sales, while smart-bots are for customer service.

d)

Script-bots are AI-powered, while smart-bots are not.

39.

What is the main advantage of lemmatization over stemming?

a)

It is better for identifying stop words.

b)

It always produces meaningful words.

c)

It is less complex.

d)

It is faster.

40.

What is the process of breaking a large body of text into structural paragraphs, sentences, and words?

a)

Discourse Integration

b)

Lexical Analysis

c)

Syntactic Analysis

d)

Pragmatic Analysis

41.

The TFIDF value of a word like "and" or "the" in a large corpus is typically:

a)

High

b)

Low or zero

c)

Highly variable

d)

Dependent on its grammatical role

42.

In the context of NLP, what does "Discourse Integration" refer to?

a)

The process of converting text to lowercase.

b)

The process of checking the grammar.

c)

The process of forming a coherent story between sentences.

d)

The process of breaking down words into their root forms.

43.

Which of the following is an example of a "No-Code" NLP tool?

a)

NLTK

b)

SpaCy

c)

Orange Data Mining

d)

Python

44.

What is the primary goal of the "Test Yourself" questions mentioned in the document?

a)

To introduce new concepts.

b)

To demonstrate the use of no-code tools.

c)

To review the user's understanding of the topic.

d)

To provide examples of NLP applications.

45.

What is the purpose of the log function in the TFIDF formula?

a)

To make the calculation faster.

b)

To prevent the IDF value from becoming too large and to scale it.

c)

To make the TF value larger.

d)

To calculate the frequency of words.

46.

What is the final output of the text processing pipeline that leads to the Bag of Words model?

a)

A list of all documents.

b)

A document vector table with word frequencies.

c)

The original text with stop words removed.

d)

A set of grammatical rules.

47.

What is the primary purpose of Natural Language Processing (NLP)?

a)

Create fonts and layouts for digital documents

b)

Build faster computer hardware for text tasks

c)

Enable computers to understand and process human language

d)

Translate human languages to numbers only

48.

Which statement best describes natural languages over time?

a)

They remain fixed without any change

b)

They change and evolve over time

c)

They are defined only by dictionaries

d)

They follow strict mathematical rules

49.

What do autogenerated captions primarily do in videos?

a)

Convert images into spoken words

b)

Summarize long videos into notes

c)

Turn speech into text in real time

d)

Translate text between languages

50.

What is syntactic analysis (parsing) mainly used to check?

a)

Real‑world relevance of statements

b)

Emotional tone of the sentence

c)

Speaker identity in audio clips

d)

Grammar and logical structure of sentences

51.

During semantic analysis, what is checked in the input text?

a)

Only punctuation and spacing

b)

Only the order of words in a sentence

c)

Speaker intent beyond the literal text

d)

Meaning of words and phrases for sense

52.

Pragmatic analysis focuses on which aspect of a sentence?

a)

Real‑world relevance and intended meaning

b)

Converting uppercase to lowercase letters

c)

Literal dictionary meaning only

d)

Counting unique words and their frequency

53.

What is a corpus in NLP?

a)

A tool for tagging parts of speech

b)

A single paragraph of text data

c)

A collection of written texts combined

d)

A list of stop words for removal

54.

What does tokenization do in text processing?

a)

Labels sentences with their sentiment

b)

Combines many documents into one

c)

Divides text into smaller units called tokens

d)

Removes rare words from the dataset

55.

Which best defines stop words in text analysis?

a)

Rare words that carry deep meaning

b)

Proper nouns requiring special handling

c)

All words shorter than four letters

d)

Very frequent words adding little meaning

56.

Which statement correctly contrasts lemmatization and stemming?

a)

Stemming ensures valid words while lemmatization does not

b)

Lemmatization returns meaningful lemmas while stemming may not

c)

Both only remove vowels from the words

d)

Both produce valid dictionary base forms

57.

In a Bag of Words model, what matters for representing text?

a)

Grammar and word order in sentences

b)

Unique words and their frequencies

c)

Synonyms and antonyms relationships

d)

Speaker’s emotion and context

58.

TFIDF stands for which phrase?

a)

Total Frequency–Inverse Data Factor

b)

Term Frequency–Inverse Document Frequency

c)

Token Frequency–Indexed Document Factor

d)

Text Feature–Inverse Data Frequency

59.

Which is a common application of TFIDF?

a)

Image segmentation and labeling

b)

Document classification of text data

c)

Compiling code to machine language

d)

Encrypting network communications

60.

Which platform is mentioned as no‑code for text analysis?

a)

PyTorch AutoML app

b)

MonkeyLearn web platform

c)

TensorFlow Hub online tools

d)

SpaCy desktop suite

61.

What is a chatbot best described as?

a)

A computer program simulating conversation

b)

A web browser for searching data

c)

A keyboard for faster text typing

d)

A physical robot for workshops

62.

Which action can chatbots perform for e‑commerce?

a)

Manufacture products on assembly lines

b)

Answer questions and generate sales leads

c)

Control warehouse robots with sensors

d)

Design product packaging automatically

63.

What does a low IDF value for a word like “the” indicate?

a)

It appears rarely in most documents

b)

It appears in many documents overall

c)

It always carries strong sentiment

d)

It is a proper noun in the corpus

64.

What is a lexicon in language processing?

a)

A stop word list for filtering

b)

A tool for ranking web search pages

c)

A collection of words and phrases used

d)

A grammar checker algorithm only

65.

Why convert all text to a single case during preprocessing?

a)

To make documents shorter in size

b)

To detect sarcasm more accurately

c)

To prevent treating case variants as different

d)

To remove all punctuation completely

66.

What does discourse integration aim to build across sentences?

a)

A list of all rare vocabulary words

b)

A coherent story linking sentences

c)

Randomized word order for variety

d)

A map of part‑of‑speech tags

67.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): The TFIDF value of a word like "the" in a large corpus is typically low. Reason (R): The IDF component of TFIDF gives a low value to words that appear frequently across many documents.

a)

Both A and R are true, but R is not the correct explanation of A.

b)

Both A and R are true, and R is the correct explanation of A.

c)

A is false, but R is true.

d)

A is true, but R is false.

68.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): In the Bag of Words model, the sequence of words in a sentence is irrelevant. Reason (R): The model focuses on the frequency of words rather than their grammatical relationships or order.

a)

A is true, but R is false.

b)

Both A and R are true, but R is not the correct explanation of A.

c)

A is false, but R is true.

d)

Both A and R are true, and R is the correct explanation of A.

69.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Stemming is generally faster than lemmatization. Reason (R): Stemming simply removes affixes without consulting a lexicon, whereas lemmatization ensures the resulting word is a meaningful one.

a)

Both A and R are true, and R is the correct explanation of A.

b)

A is false, but R is true.

c)

A is true, but R is false.

d)

Both A and R are true, but R is not the correct explanation of A.

70.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Sentiment Analysis is a tool to determine the underlying emotion in a text. Reason (R): It helps to automatically detect emotions when customers interact with products, services, or brands.

a)

Both A and R are true, and R is the correct explanation of A.

b)

Both A and R are true, but R is not the correct explanation of A.

c)

A is true, but R is false.

d)

A is false, but R is true.

71.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): The final stage of NLP is Pragmatic Analysis. Reason (R): Pragmatic Analysis checks the grammatical correctness of a sentence.

a)

Both A and R are true, and R is the correct explanation of A.

b)

Both A and R are true, but R is not the correct explanation of A.

c)

A is true, but R is false.

d)

A is false, but R is true.

72.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Converting text to a common case is an important step in text normalization. Reason (R): It ensures that the machine treats words like "Apple" and "apple" as the same entity.

a)

A is false, but R is true.

b)

A is true, but R is false.

c)

Both A and R are true, but R is not the correct explanation of A.

d)

Both A and R are true, and R is the correct explanation of A.

73.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): A high TFIDF value for a word indicates that it is very important for a specific document. Reason (R): The word has a high term frequency in that document but a low document frequency across the entire corpus.

a)

Both A and R are true, and R is the correct explanation of A.

b)

A is false, but R is true.

c)

Both A and R are true, but R is not the correct explanation of A.

d)

A is true, but R is false.

74.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Discourse Integration is the process of breaking down a large text into paragraphs, sentences, and words. Reason (R): Discourse Integration forms a coherent "story" by checking the relationship between successive sentences.

a)

A is false, but R is true.

b)

A is true, but R is false.

c)

Both A and R are true, but R is not the correct explanation of A.

d)

Both A and R are true, and R is the correct explanation of A.

75.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Chatbots use NLP to simulate human conversation. Reason (R): NLP enables computers to understand and process human language, which is essential for a chatbot to function effectively.

a)

Both A and R are true, and R is the correct explanation of A.

b)

Both A and R are true, but R is not the correct explanation of A.

c)

A is true, but R is false.

d)

A is false, but R is true.

76.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Semantic Analysis checks the meaningfulness of an input text. Reason (R): It is the first stage of the NLP pipeline, followed by Lexical Analysis.

a)

A is true, but R is false.

b)

A is false, but R is true.

c)

Both A and R are true, but R is not the correct explanation of A.

d)

Both A and R are true, and R is the correct explanation of A.

77.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Autogenerated captions are a real-world application of NLP. Reason (R): NLP enables the conversion of speech into text in real-time.

a)

Both A and R are true, and R is the correct explanation of A.

b)

A is true, but R is false.

c)

Both A and R are true, but R is not the correct explanation of A.

d)

A is false, but R is true.

78.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): The Bag of Words model is a method for text representation that retains the grammatical structure of sentences. Reason (R): The model disregards the sequence and grammar of words, focusing only on their frequency.

a)

Both A and R are true, but R is not the correct explanation of A.

b)

Both A and R are true, and R is the correct explanation of A.

c)

A is true, but R is false.

d)

A is false, but R is true.

79.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): The process of breaking a large body of text into smaller units like words and sentences is called Tokenization. Reason (R): Tokenization is a key step in Text Normalization, which simplifies textual data.

a)

Both A and R are true, and R is the correct explanation of A.

b)

A is true, but R is false.

c)

A is false, but R is true.

d)

Both A and R are true, but R is not the correct explanation of A.

80.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): NLTK is considered a "no-code" NLP tool. Reason (R): NLTK is a Python library that requires programming knowledge to be used for text processing.

a)

A is true, but R is false.

b)

A is false, but R is true.

c)

Both A and R are true, but R is not the correct explanation of A.

d)

Both A and R are true, and R is the correct explanation of A.

81.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Keyword Extraction is used to automatically identify the most important words from a text. Reason (R): It helps provide valuable insights into the main topics or themes of a document.

a)

Both A and R are true, and R is the correct explanation of A.

b)

Both A and R are true, but R is not the correct explanation of A.

c)

A is false, but R is true.

d)

A is true, but R is false.

82.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): A word with a high TFIDF value is typically a stop word. Reason (R): A high TFIDF value indicates that the word is rare in the corpus but has a high frequency in a specific document.

a)

A is true, but R is false.

b)

Both A and R are true, but R is not the correct explanation of A.

c)

Both A and R are true, and R is the correct explanation of A.

d)

A is false, but R is true.

83.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): The Syntactic Analysis stage of NLP checks for the meaningfulness of a sentence. Reason (R): Semantic Analysis, not Syntactic Analysis, is responsible for checking if a sentence is meaningful.

a)

Both A and R are true, but R is not the correct explanation of A.

b)

A is false, but R is true.

c)

A is true, but R is false.

d)

Both A and R are true, and R is the correct explanation of A.

84.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): Natural languages are static and do not change over time. Reason (R): One of the features of natural languages is that they are constantly changing and evolving.

a)

A is false, but R is true.

b)

A is true, but R is false.

c)

Both A and R are true, but R is not the correct explanation of A.

d)

Both A and R are true, and R is the correct explanation of A.

85.

Directions: Choose the correct option from the following: (a) Both A and R are true, and R is the correct explanation of A. (b) Both A and R are true, but R is not the correct explanation of A. (c) A is true, but R is false. (d) A is false, but R is true. Assertion (A): A script-bot is an AI-powered chatbot that can learn from user interactions. Reason (R): Script-bots are limited to a pre-defined set of scripted responses.

a)

Both A and R are true, but R is not the correct explanation of A.

b)

A is false, but R is true.

c)

A is true, but R is false.

d)

Both A and R are true, and R is the correct explanation of A.

86.

Which statement best describes a high TF-IDF value for a word in a document?

a)

Appears often in this document but rare in corpus

b)

Appears rarely and common across corpus

c)

Appears equally across documents and corpus

d)

Appears often across corpus but rare in document

87.

Which NLP stage primarily checks the meaningfulness of an input text?

a)

Speech Recognition

b)

Discourse Integration

c)

Semantic Analysis

d)

Lexical Analysis

88.

In Discourse Integration, what is mainly examined to form a coherent story?

a)

Word frequency within one sentence

b)

Order of letters in every word

c)

Length of each paragraph

d)

Relationships between adjacent sentences

89.

What is a core limitation of the Bag of Words model?

a)

Cannot handle rare words at all

b)

Ignores grammatical structure and word order

c)

Requires labeled training data

d)

Only works with spoken language

90.

What does tokenization do during text processing?

a)

Converts audio to text

b)

Breaks text into smaller units called tokens

c)

Assigns parts of speech to every token

d)

Removes stopwords from the corpus

91.

Which best describes text normalization in NLP?

a)

Cleaning and simplifying text for processing

b)

Rendering text as spoken audio output

c)

Predicting next words in a sentence

d)

Encrypting messages for secure transfer

92.

What is the primary goal of keyword extraction?

a)

Generate longer summaries from short notes

b)

Translate sentences between human languages

c)

Sort documents alphabetically by title

d)

Identify main terms that capture document themes

93.

In a corpus, what does the IDF component of TF‑IDF indicate?

a)

Rarity of a word across many documents

b)

Length of a sentence within one document

c)

Order of words inside a single sentence

d)

Grammar correctness of the entire corpus

94.

Which operation is commonly part of text normalization?

a)

Converting all text to lowercase case

b)

Counting the number of pages

c)

Applying data compression algorithms

d)

Embedding watermarks in files

95.

Stemming and lemmatization are used to:

a)

Reduce words to base forms for analysis

b)

Translate words into phonetic spelling

c)

Encrypt vocabulary for secure storage

d)

Detect sarcasm in social media posts

96.

Which statement about Bag of Words is accurate?

a)

Represents text by word frequencies, ignoring order

b)

Stores meanings using a predefined ontology

c)

Encodes grammar rules for sentence generation

d)

Tracks word positions to preserve full sequence

97.

Why convert text to a common case like lowercase?

a)

Avoid treating same words as different tokens

b)

Comply with hardware voltage limitations

c)

Increase the speed of internet connectivity

d)

Improve image clarity in scanned documents

98.

Which example best shows context ambiguity?

a)

The date "2024" meaning a calendar year

b)

The word "triangle" meaning a polygon

c)

The number "two" meaning exactly two

d)

The word "red" meaning color or emotion

99.

What does a chatbot mainly do in NLP applications?

a)

Draws charts from numeric spreadsheet cells

b)

Measures internet latency for diagnostics

c)

Simulates human conversation to assist users

d)

Compiles source code into machine binaries

100.

Which difference between script‑bots and smart‑bots is correct?

a)

Script‑bots use fixed replies; smart‑bots learn

b)

Both learn continuously from every dialogue

c)

Smart‑bots ignore context; script‑bots model it

d)

Script‑bots are only voice; smart‑bots only text

101.

Which best defines a corpus in text processing?

a)

Entire collection of documents for analysis

b)

Printed dictionary used by linguists

c)

Single sentence chosen for demonstration

d)

Encrypted archive for long‑term backups

102.

How do voice assistants like Alexa use NLP?

a)

Process speech to understand intent and act

b)

Render videos by enhancing audio playback

c)

Design microchips using logical circuits

d)

Detect malware by scanning network packets

103.

Which outcome distinguishes lemmatization from stemming?

a)

Converts words to phonetic syllables

b)

Removes all vowels from each token

c)

Always yields longer word variants

d)

Produces meaningful dictionary lemmas

104.

What key limitation of Bag of Words should students recall?

a)

Fails to count repeated words in texts

b)

Requires labeled data for supervised learning

c)

Only works on languages without inflection

d)

Ignores word order and sequence information

105.

Which task is best served by keyword extraction in a news app?

a)

Predict stock prices from trading volumes

b)

Tag each article with main topics quickly

c)

Render headlines into artistic fonts

d)

Compress images to reduce bandwidth

106.

Which statement about TF‑IDF weights is most accurate?

a)

High when terms are frequent in a document but rare in corpus

b)

High when terms are common stop words across the entire corpus

c)

Independent of term frequency within the specific document

d)

Zero for every term that appears in any document of the corpus

107.

Which step is NOT part of the Bag of Words workflow described?

a)

Aggregate rows into a document vector table

b)

Create document vectors for word counts

c)

Train a neural network for embeddings

d)

Create a dictionary of unique words

e)

Build a final table of document frequencies

108.

In Bag of Words, what does a document vector table primarily contain?

a)

Syntactic parse trees for documents

b)

Sentiment labels for each sentence

c)

Frequencies of unique words per document

d)

Entity types linked to each token

e)

Topic labels predicted for each file

109.

What is the main purpose of stop word removal during normalization?

a)

Normalize numbers into a common scale

b)

Add context from neighboring sentences

c)

Increase the vocabulary size significantly

d)

Focus on more meaningful terms in text

e)

Convert words to their base dictionary form

110.

Which pair correctly lists no-code tools and code-based tools?

a)

SpaCy and Orange; NLTK and MonkeyLearn

b)

Orange and MonkeyLearn; NLTK and SpaCy

c)

NLTK and Orange; SpaCy and MonkeyLearn

d)

NLTK and SpaCy; Orange and MonkeyLearn

e)

MonkeyLearn and SpaCy; NLTK and Orange

111.

In TF-IDF, why is a logarithm used in the IDF calculation?

a)

To scale down extreme IDF values

b)

To remove negative term frequencies

c)

To convert counts into probabilities

d)

To boost common words exponentially

e)

To average TF across all documents

112.

Which feature is NOT listed as a property of natural languages?

a)

Structured with semantics for sentences

b)

Deterministic with fixed meanings always

c)

Dynamic and evolving over time

d)

Redundant with multiple phrasing options

e)

Governed by rules like syntax and lexicon

113.

Syntactic analysis primarily checks what in NLP?

a)

Grammatical structure and relationships

b)

Speaker intent across conversations

c)

Document-level topic distributions

d)

Real-world relevance and sarcasm

e)

Frequency of rare words globally

114.

Semantic analysis verifies that words and phrases are

a)

Aligned to speaker’s real intent

b)

Weighted by inverse document frequency

c)

Used meaningfully within the sentence

d)

Linked to named entities correctly

e)

Statistically independent across tokens

115.

Text normalization is important mainly because it

a)

Detects topics without labeled data

b)

Adds new words to the corpus automatically

c)

Translates documents into other languages

d)

Simplifies text for later processing steps

e)

Generates embeddings from character n-grams

116.

Which is NOT an application of TF-IDF listed in the material?

a)

Document classification by content importance

b)

Topic modeling to find central themes

c)

Information retrieval to rank relevant terms

d)

Speech recognition for phoneme timing

e)

Highlighting unique words in a corpus

117.

A chatbot processes user input through stages including

a)

Supervised, unsupervised, reinforcement

b)

Lexical, syntactic, semantic, discourse, pragmatic

c)

Optical, acoustic, visual, spatial, tactile

d)

Token, lemma, stem, root, morpheme only

e)

Heuristic, genetic, simulated annealing

118.

A higher final TF-IDF value for a word suggests it is

a)

Weighted down by high document counts

b)

Only frequent within the entire corpus

c)

Irrelevant due to low term frequency

d)

Important in a document but rare overall

e)

Common everywhere and not informative

119.

Why is context important in NLP, as shown by the word “red”?

a)

Context guarantees literal interpretation

b)

Context only affects punctuation decisions

c)

Context can change a word’s intended meaning

d)

Context removes the need for tokenization

e)

Context assigns a fixed universal meaning

120.

Text classification mainly

a)

Translates texts into target languages

b)

Assigns texts to predefined categories

c)

Generates summaries from long articles

d)

Clusters texts without categories

e)

Parses texts into dependency trees

121.

During normalization, removing special characters and numbers is done to

a)

Create new stemming dictionaries

b)

Ensure all tokens are stop words

c)

Preserve email IDs in every dataset

d)

Eliminate tokens not useful for analysis

e)

Increase the corpus size intentionally

122.

Pragmatic analysis focuses on

a)

Literal meaning only within grammar

b)

Real-world intent beyond literal text

c)

Counting words across documents

d)

Generating the final document vector

e)

Assigning parts of speech to tokens

123.

Keyword extraction can help a business by

a)

Translating posts into multiple languages

b)

Automatically pulling key words and phrases

c)

Encrypting customer feedback for privacy

d)

Replacing human agents with chatbots

e)

Measuring exact sentence grammar rules

124.

In TF and DF, which statement is correct?

a)

Both TF and DF are always equal values

b)

DF measures occurrences within single file

c)

TF is number of documents containing a term

d)

TF counts across all documents globally

e)

DF is number of documents where term appears

125.

Why is stemming faster than lemmatization according to the material?

a)

It ensures words become meaningful lemmas

b)

It computes POS tags for each token

c)

It expands words to original root forms

d)

It checks a lexicon for valid lemmas

e)

It removes affixes without dictionary checks

126.

Which stage of an NLP pipeline identifies tokens like "The", "quick", and "brown" from a sentence?

a)

Semantic meaning check

b)

Pragmatic intent check

c)

Lexical analysis of tokens

d)

Syntactic grammar check

e)

Discourse coherence check

127.

In TF-IDF, what does the IDF component primarily do for very common words across documents?

a)

Penalizes their importance

b)

Raises their frequency

c)

Ignores their occurrences

d)

Duplicates their counts

e)

Converts them to lowercase

128.

During text normalization, which step removes words like "the", "is", and symbols before stemming?

a)

Sentence segmentation step

b)

Converting to common case

c)

Tokenization into words

d)

Removing stop words and symbols

e)

Pragmatic analysis step

129.

A chatbot built with fixed rules and unable to adapt beyond its script is best described as a:

a)

Context-bot with plans

b)

Neural-bot with vision

c)

Hybrid-bot with memory

d)

Smart-bot with learning

e)

Script-bot with rules

130.

Given TF=3 for word "game" in a document and IDF=log(10/2), which expression equals its TF-IDF?

a)

log(3 × 10/2)

b)

3 × log(2/10)

c)

3 + log(10/2)

d)

log(10/2) ÷ 3

e)

3 × log(10/2)

131.

After normalization steps, which lemmatized token list best matches Document 2: "Akash likes to play football, but Ajay prefers to play online games"?

a)

[akash, likes, to, play, football, ajay, prefers, to, play, online, games]

b)

[akash, like, to, plays, football, ajay, prefer, online, gaming]

c)

[akash, like, to, play, football, ajay, prefer, to, play, online, game]

d)

[Akash, like, play, football, Ajay, prefer, play, game]

e)

[akash, ajay, best, friend]

132.

After preprocessing the corpus [D1: "Aman and Avni are stressed", D2: "Aman went to a therapist", D3: "Avni went to download a health chatbot"], which set correctly represents the dictionary (unique words) for a Bag of Words model when lowercase conversion and stop-word removal are applied?

a)

{aman, avni, stressed, went, therapist, download, health, chatbot}

b)

{aman, avni, stressed, are, went, to, therapist, health}

c)

{Aman, Avni, stressed, went, therapist, download, health, chatbot}

d)

{aman, avni, are, went, to, therapist, download, chatbot}

133.

Which vector correctly represents Document 1 in the created Bag of Words vectors using the dictionary order [aman, avni, stressed, went, therapist, download, health, chatbot]?

a)

[1, 0, 1, 0, 1, 0, 0, 0]

b)

[1, 0, 0, 1, 0, 0, 0, 0]

c)

[1, 1, 1, 0, 0, 0, 0, 0]

d)

[0, 1, 0, 1, 0, 1, 1, 1]

134.

Which statement best explains why TFIDF helps with stop word filtering in text processing?

a)

Common words have high DF so low TFIDF values

b)

Rare words have high DF so high TFIDF values

c)

Common words have low DF so high TFIDF values

d)

Rare words have low TF so low TFIDF values

135.

Given the corpus of four documents where the word "Papa" appears in three documents and appears once in Document 2, which TFIDF value for "Papa" in Document 2 is closest when using TFIDF = TF × log(Total Docs / Docs with term)?

a)

0.333

b)

0.000

c)

1.333

d)

0.125

136.

NLP stands for ________.

a)

None of the above

b)

None Language Processing

c)

Nature Language Processing

d)

Natural Language Processing

137.

__________, is the sub-field of AI that is focused on enabling computers to understand and process human languages.

a)

Computer Vision

b)

None of the above

c)

Data Science

d)

Natural Language Processing

138.

__________ is the sub-field of AI that make the interactions between computers and human (natural) languages

a)

None of the above

b)

Natural Language Processing

c)

Computer Vision

d)

Data Science

139.

Which of the games below is related to natural language processing?

a)

Voice Assistants

b)

Chatbots

c)

Mystery Animal

d)

Grammar Checkers

140.

Applications of Natural Language Processing

a)

Automatic Summarization

b)

All of the above

c)

Text Classification

d)

Sentiment Analysis

141.

__________ Information overload is a real problem when we need to access a specific, important piece of information from a huge knowledge base.

a)

All of the above

b)

Text Classification

c)

Sentiment Analysis

d)

Automatic Summarization

142.

__________ is especially relevant when used to provide an overview of a news item or blog post, while avoiding redundancy from multiple sources and maximizing the diversity of content obtained.

a)

All of the above

b)

Automatic Summarization

c)

Sentiment Analysis

d)

Text Classification

143.

The goal of sentiment analysis is to identify sentiment among several posts or even in the same post where emotion is not always explicitly expressed.

a)

Automatic Summarization

b)

Sentiment Analysis

c)

Text Classification

d)

All of the above

144.

Companies use Natural Language Processing applications, such as __________, to identify opinions and sentiment online to help them understand what customers think about their products and services

a)

Automatic Summarization

b)

Sentiment Analysis

c)

Text Classification

d)

All of the above

145.

__________ makes it possible to assign predefined categories to a document and organize it to help you find the information you need or simplify some activities.

a)

Text Classification

b)

Sentiment Analysis

c)

Automatic Summarization

d)

All of the above

146.

__________ device helps to communicate with humans and abilities to make humans lives easier.

a)

Siri

b)

Google Assistant

c)

All of the above

d)

Cortana

147.

__________ is all about how machines try to understand and interpret human language and operate accordingly.

a)

None of the above

b)

Computer Vision

c)

Data Science

d)

Natural Language Processing

148.

By dividing up large problems into smaller ones, __________ aims to help you manage them in a more constructive manner.

a)

CDP

b)

CLP

c)

CBT

d)

CSP

149.

CBT stands for ___________.

a)

Common Behavioural Therapy (CBT)

b)

Cognitive Behavioural Therapy (CBT)

c)

None of the above

d)

Connection Behavioural Therapy (CBT)

150.

Cognitive behavioural Therapy includes __________.

a)

Your Thoughts

b)

All of the above

c)

Your Behaviors

d)

Your Emotions