Natural Language Processing Questions

Multiple Choice Questions

1. What is the primary goal of Natural Language Processing (NLP)?
a) To create visually appealing interfaces
b) To enable machines to understand and derive meaning from human lan-
guages
c) To process numerical data efficiently
d) To enhance image recognition capabilities

2. Which field is combined with computer science in NLP to decipher lan-

guage structure?
a) Physics
b) Linguistics
c) Biology
d) Chemistry

3. What is a corpus in the context of NLP?

a) A single sentence in a document
b) A collection of documents or text files
c) A type of machine learning algorithm
d) A visual representation of data

4. In NLP, what is a document composed of?

a) Pixels
b) Sentences
c) Algorithms
d) Images

5. What is the first step in the NLP pipeline?

a) Word Tokenization
b) Sentence Segmentation
c) Stemming
d) Lemmatization

6. What does word tokenization involve?

a) Breaking a sentence into individual words or tokens

1
 b) Grouping words into sentences
c) Removing punctuation from text
d) Assigning parts of speech to words

7. What is the purpose of stemming in NLP?

a) To assign grammatical tags to words
b) To normalize words into their base or root form
c) To translate text into another language
d) To remove stop words from text

8. What is a key difference between stemming and lemmatization?

a) Stemming produces a root word that always has meaning, while lemma-
tization may not
b) Lemmatization produces a root word that has meaning, while stemming
may not
c) Stemming is used for translation, while lemmatization is used for tok-
enization
d) Lemmatization removes stop words, while stemming does not

9. Which of the following is considered a stop word?

a) Star
b) The
c) Twinkling
d) Night

10. What does POS tagging stand for in NLP?

a) Positive Sentiment Tagging
b) Part of Speech Tagging
c) Processing of Sentences
d) Pattern of Speech Tagging

11. What is the purpose of Named Entity Recognition (NER)?

a) To break sentences into tokens
b) To detect named entities like person names or locations
c) To normalize words to their root form
d) To remove stop words from text

12. Which of the following is an application of NLP?

a) Image enhancement
b) Sentiment analysis
c) Pixel processing
d) Optical illusion correction

13. What does sentiment analysis predict in a review?

a) The length of the review

2
 b) Whether the review is positive, negative, or neutral
c) The language of the review
d) The author of the review

14. What is a characteristic of bilingual machine translation systems?

a) They translate between any pair of languages
b) They use an intermediate language called Interlingua
c) They translate directly from source to target language
d) They focus on image processing

15. What is the role of NLP in spam filtering?

a) To enhance image quality
b) To identify unwanted emails
c) To compress data
d) To generate visual illusions

16. What is automatic summarization in NLP?

a) Creating a detailed analysis of text
b) Generating a short, accurate summary of longer text
c) Translating text into multiple languages
d) Tagging parts of speech in sentences

17. What is a challenge for NLP in question-answering systems?

a) Image resolution
b) Lexical gap
c) Pixel intensity
d) Color spectrum

18. What does Natural Language Interaction (NLI) enable?

a) Interaction with devices using binary code
b) Humanlike interaction with connected devices
c) Image processing in real-time
d) Data compression for storage

19. Which of the following is an example of conversational AI?

a) Image editing software
b) ChatGPT
c) Pixel analysis tool
d) Optical character recognition

20. What is the main focus of computer vision?

a) Processing and analyzing visual data
b) Understanding human languages
c) Compressing text data
d) Normalizing word forms

3
21. How does computer vision differ from human vision?
a) It is limited to the visible spectrum
b) It can process data beyond the visible spectrum
c) It cannot process images
d) It relies on human memory

22. What is a key requirement for computer vision?

a) Knowledge in linguistics
b) Deep learning models like CNN and RNN
c) Tokenization algorithms
d) Stop word removal

23. What is image processing primarily concerned with?

a) Enhancing or extracting information from images
b) Translating text into images
c) Normalizing words in text
d) Assigning parts of speech

24. How is an image represented in computer vision?

a) As a collection of sentences
b) By its dimensions based on the number of pixels
c) As a set of tokens
d) As a corpus of text

25. What does each pixel in a grayscale image represent?

a) A sentence
b) A brightness value
c) A part of speech
d) A named entity

26. Which of the following is a flaw of human vision mentioned in the docu-
ment?
a) Inability to process text
b) Limited memory for quickly flashed images
c) Inability to process binary data
d) Lack of linguistic understanding

27. What is a token in the context of NLP?

a) A complete document
b) A single word or punctuation mark
c) A collection of documents
d) A machine learning model

28. What is the output of sentence segmentation?

4
 a) Individual words
b) Separate sentences
c) Root words
d) Named entities

29. Which step in the NLP pipeline involves assigning grammatical roles to
words?
a) Tokenization
b) POS Tagging
c) Stemming
d) Lemmatization

30. What is a limitation of stemming compared to lemmatization?

a) It requires more computational power
b) It may produce a root word without meaning
c) It cannot process multiple languages
d) It removes essential words

31. Which NLP application involves creating short summaries of text?

a) Sentiment Analysis
b) Automatic Summarization
c) Spam Filtering
d) Question-Answering

32. What does a multilingual MT system use to translate languages?

a) Direct translation
b) Interlingua approach
c) POS tagging
d) Tokenization

33. What is a benefit of removing stop words in NLP?

a) Increases processing speed
b) Enhances image quality
c) Improves translation accuracy
d) Assigns grammatical tags

34. Which of the following is NOT a use case of NLP?

a) Language Translation
b) Speech Recognition
c) Image Enhancement
d) Sentiment Analysis

35. What does conversational AI aim to achieve?

a) Process numerical data
b) Understand complex conversational input

5
 c) Enhance image resolution
d) Normalize text data

36. What is the role of deep learning in computer vision?

a) To tokenize sentences
b) To process and analyze visual data
c) To remove stop words
d) To translate languages

37. What is a common issue addressed by spam filtering?

a) Unwanted emails
b) Image compression
c) Text translation
d) Pixel analysis

38. In NLP, what is the purpose of text cleaning?

a) To enhance image quality
b) To prepare text for further processing
c) To assign parts of speech
d) To compress data

39. Which of the following is an example of a named entity?

a) The
b) Tim Cook
c) Are
d) Twinkling

40. What is the final step mentioned in the NLP pipeline before applying a ma-
chine learning algorithm?
a) Sentence Segmentation
b) Lemmatization
c) POS Tagging
d) Named Entity Recognition

41. Which machine learning algorithm is mentioned as an example for creat-

ing an NLP application?
a) K-Means Clustering
b) Naive Bayes
c) Decision Trees
d) Linear Regression

42. What is a characteristic of a digital image in computer vision?

a) A collection of sentences
b) A binary representation of visual data
c) A set of tokens

6
 d) A corpus of documents

43. What does lemmatization ensure about the root word?

a) It is always meaningless
b) It has a valid meaning
c) It is a stop word
d) It is a named entity

44. What is the purpose of auto-correct in NLP?

a) To enhance images
b) To correct grammar and spellings
c) To process numerical data
d) To remove stop words

45. Which of the following is a challenge in building a question-answering sys-

tem?
a) Image resolution
b) Ambiguity
c) Pixel intensity
d) Color spectrum

46. What type of data does NLP primarily process?

a) Numerical data
b) Unstructured textual data
c) Image data
d) Binary data

47. What is the role of computer vision in relation to AI?

a) To enable computers to think
b) To enable computers to see
c) To translate languages
d) To normalize text

48. Which of the following is a type of machine translation system?

a) POS Tagging
b) Bilingual MT
c) Stop Word Removal
d) Sentence Segmentation

49. What is the primary difference between image processing and computer
vision?
a) Image processing focuses on cognitive operations, while computer vision
enhances images
b) Computer vision involves cognitive operations, while image processing
enhances or extracts information

7
 c) Image processing uses NLP techniques, while computer vision does not
d) Computer vision processes text, while image processing does not

50. What does the Interlingua approach in multilingual MT involve?

a) Direct translation from source to target language
b) Translation to an intermediate language before the target language
c) Removal of stop words
d) Assigning parts of speech

Fill in the Blank Questions

1. The process of breaking a document into its constituent sentences is called
.

2. A is a collection of documents or text files in NLP.

3. In NLP, a single word or punctuation mark is referred to as a .

4. The process of normalizing words into their base form is known as .

5. is used to group different inflected forms of a word into its lemma.

6. Words like ”is” and ”the” are called words in NLP.

7. tagging assigns grammatical roles like nouns or verbs to words.

8. Named Entity Recognition (NER) detects entities such as names

or locations.

9. analysis predicts whether a review is positive, negative, or neu-

tral.

10. A MT system translates directly from the source to the target lan-
guage.

11. The approach in multilingual MT uses an intermediate language.

12. filtering is an NLP application used to identify unwanted emails.

13. Automatic creates short, accurate summaries of longer texts.

8
14. is a challenge in NLP question-answering systems due to multi-
ple meanings of words.

15. Natural Language enables humanlike interaction with devices.

16. AI allows technology to understand complex conversational in-

put.

17. vision is the field that enables computers to process visual data
like images.

18. Image is a subdomain of computer vision focused on enhancing

or extracting information from images.

19. In a grayscale image, each pixel represents a value.

20. A digital image is a representation of visual data.

True/False Questions
1. NLP combines linguistics and computer science to understand human lan-
guages.

2. Stemming always produces a root word that has a valid meaning.

3. Stop words are essential for understanding the meaning of a sentence.

4. POS tagging involves assigning grammatical roles to words.

5. Named Entity Recognition (NER) is used to remove stop words from text.

6. Sentiment analysis is an application of computer vision.

7. Bilingual MT systems translate directly from source to target language.

8. Computer vision is limited to the visible spectrum, like human vision.

9. Image processing is a subdomain of computer vision.

10. NLP primarily processes structured numerical data.

9
10
Answer Key
Multiple Choice Answers
1. b) To enable machines to understand and derive meaning from human lan-
guages
2. b) Linguistics
3. b) A collection of documents or text files
4. b) Sentences
5. b) Sentence Segmentation
6. a) Breaking a sentence into individual words or tokens
7. b) To normalize words into their base or root form
8. b) Lemmatization produces a root word that has meaning, while stemming
may not
9. b) The
10. b) Part of Speech Tagging
11. b) To detect named entities like person names or locations
12. b) Sentiment analysis
13. b) Whether the review is positive, negative, or neutral
14. c) They translate directly from source to target language
15. b) To identify unwanted emails
16. b) Generating a short, accurate summary of longer text
17. b) Lexical gap
18. b) Humanlike interaction with connected devices
19. b) ChatGPT
20. a) Processing and analyzing visual data
21. b) It can process data beyond the visible spectrum
22. b) Deep learning models like CNN and RNN
23. a) Enhancing or extracting information from images
24. b) By its dimensions based on the number of pixels
25. b) A brightness value
26. b) Limited memory for quickly flashed images
27. b) A single word or punctuation mark
28. b) Separate sentences
29. b) POS Tagging
30. b) It may produce a root word without meaning

11
 31. b) Automatic Summarization
32. b) Interlingua approach
33. a) Increases processing speed
34. c) Image Enhancement
35. b) Understand complex conversational input
36. b) To process and analyze visual data
37. a) Unwanted emails
38. b) To prepare text for further processing
39. b) Tim Cook
40. d) Named Entity Recognition
41. b) Naive Bayes
42. b) A binary representation of visual data
43. b) It has a valid meaning
44. b) To correct grammar and spellings
45. b) Ambiguity
46. b) Unstructured textual data
47. b) To enable computers to see
48. b) Bilingual MT
49. b) Computer vision involves cognitive operations, while image processing
enhances or extracts information
50. b) Translation to an intermediate language before the target language

Fill in the Blank Answers

1. Sentence Segmentation
2. Corpus
3. Token
4. Stemming
5. Lemmatization
6. Stop
7. POS
8. Person
9. Sentiment
10. Bilingual
11. Interlingua
12. Spam

12
13. Summarization
14. Ambiguity
15. Interaction
16. Conversational
17. Computer
18. Processing
19. Brightness
20. Binary

True/False Answers
1. True
2. False
3. False
4. True
5. False
6. False
7. True
8. False
9. True
10. False

13