Practice Natural Language Processing Class 10 Extra Questions and Answers to strengthen your understanding of important concepts related to Natural Language Processing (NLP) and Artificial Intelligence. These extra questions cover key topics in a simple and easy-to-understand format, helping Class 10 students revise the chapter, improve their knowledge, and prepare for school and board examinations.
Natural Language Processing Class 10 Extra Questions and Answers
Q. You are developing a chatbot for a university admission system. The bot should understand queries like тАЬWhat are the admission requirements?тАЭ and тАЬWhen is the deadline?тАЭ Which NLP stages would be most critical for this application?
a. Only Lexical Analysis
b. Lexical and Syntactic Analysis
c. All stages from lexical to pragmatic analysis
d. Only Semantic Analysis
Answer: c. All stages from lexical to pragmatic analysis.
Q. A company wants to analyse customer reviews to understand satisfaction levels. Which NLP application would be most suitable?
a. Text classification
b. Sentiment analysis
c. Keyword extraction
d. Language translation
Answer: b. Sentiment analysis.
Q. The sentence тАЬhot ice creamтАЭ would be rejected at which stage of NLP processing?
a. Lexical Analysis
b. Syntactic Analysis
c. Semantic Analysis
d. Discourse Integration
Answer: c. Semantic Analysis.
Q. With reference to text normalisation, which of the following is NOT an example of a stop word?
a. into
b. as
c. $
d. healed
Answer: d. healed.
Q. Assertion (A) : Sentiment analysis can help businesses improve customer service.
Reason (R) : It automatically detects emotions when customers interact with products or services.
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.
Answer: a. Both (A) and (R) are true, and (R) is the correct explanation of (A).
Q. Which NLP application would be most useful for a hearing-impaired person watching a live news broadcast?
a. Language translation
b. Voice assistants
c. Auto-generated captions
d. Sentiment analysis
Answer: c. AutoтАСgenerated captions.
Q. Which NLP application helps in converting natural speech into text in real time?
a. Keyword extraction tool
b. Translation of books from the English to the Hindi language
c. Auto-generated captions on YouTube
d. Classifying raw text into pre-defined groups
Answer: c. AutoтАСgenerated captions on YouTube.
Q. Which type of chatbot requires coding and works on bigger databases directly?
a. Script bot
b. Smart bot
c. Traditional bot
d. Rule-based bot
Answer: b. Smart bot.
Q. Which of the following words represents an example of stemming for тАЬsharingтАЭ?
a. Share
b. Shared
c. Shares
d. Shar
Answer: d. Shar.
Q. Assertion (A) : Converting text to lowercase is preferable in text preprocessing.
Reason (R) : It ensures that тАЬHelloтАЭ and тАЬhelloтАЭ are treated as the same word by the machine.
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
Answer: a. Both (A) and (R) are true and (R) is the correct explanation of (A).
Q. In the sentence тАЬShe reads the bookтАЭ, which of the following is a stop word that should be removed during text preprocessing?
a. She
b. reads
c. the
d. book
Answer: c. the.
Q. In Natural Language Processing (NLP), ___________ occur/s very frequently in the corpus but do/does not add any value to it.
a. Text Normalisation
b. Stop words
c. Start words
d. Tokenisation
Answer: b. Stop words.
Q. The first step of Bag of Words algorithm is text normalisation. Which of the following tasks is done in this step?
a. Creating document vectors
b. Collecting and preprocessing data
c. Adding the words to a dictionary
d. Creating a vector of words
Answer: b. Collecting and preтАСprocessing data.
Q. Consider the following sentence:
On seeing her sonтАЩs result, PoojaтАЩs face turned red with anger. The word тАЬredтАЭ demonstrates which characteristic of natural language ?
a. Redundancy
b. Context-dependent meaning
c. Grammatical structure
d. Temporal change
Answer: b. ContextтАСdependent meaning.
Q. Sentiment analysis of customer reviews on various online stores is an example of ____________.
a. Machine Learning
b. Computer Vision
c. Natural Language Processing (NLP)
d. Speech Recognition
Answer: c. Natural Language Processing (NLP).
Q. How is stemming different from lemmatisation? Explain how the word тАЬwolvesтАЭ would be processed by stemming and lemmatisation.
Answer:
Stemming removes affixes but may give nonтАСmeaningful root.
тЖТ тАЬWolvesтАЭ тЖТ тАЬWolvтАЭ (not meaningful).
Lemmatisation removes affixes but ensures meaningful words.
тЖТ тАЬWolvesтАЭ тЖТ тАЬWolfтАЭ (correct meaningful word).
Q. With reference to NLP, list the first four steps involved in text normalisation.
Answer:
- Sentence Segmentation тАУ break text into sentences.
- Tokenisation тАУ split sentences into words/tokens.
- Removing Stop Words, Special Characters, Numbers тАУ remove useless words like тАЬtheтАЭ, тАЬisтАЭ.
- Converting Text to Common Case тАУ usually lowercase.
Q. Identify the stage of NLP and explain.
We are to the zoo going tomorrow.
We are going to the zoo tomorrow.
Answer: Stage тАУ Syntactic Analysis (Parsing). It checks grammar and word order.
Q. Categorise the following examples under the given three AI domains. Data Science, NLP and Computer Vision with justification:
a. Recommendation Websites
b. Voice-based Virtual Assistants
c. Spam Filters
d. Airline Route Planning
Answer:
- a) Recommendation Websites тАУ Data Science. They use data patterns to suggest items.
- b) VoiceтАСbased Virtual Assistants тАУ NLP. They process speech and respond.
- c) Spam Filters тАУ NLP. They classify emails as spam or not.
- d) Airline Route Planning тАУ Data Science. It uses data analysis for best routes.
Q. Read the following three documents and answer the questions that follow:
тЧП Document 1: тАЬStudents love studying AIтАЭ
тЧП Document 2: тАЬAI is transforming educationтАЭ
тЧП Document 3: тАЬTeachers and students explore AI toolsтАЭ
After performing basic text preprocessing (removing punctuation, converting to lowercase, and tokenising), the documents become:
тЧП Document 1: [students, love, studying, ai]
тЧП Document 2: [ai, is, transforming, education]
тЧП Document 3: [teachers, students, explore, ai, tools]
Questions:
a) Create the dictionary (vocabulary) of unique words from all three documents.
Answer: [students, love, studying, ai, is, transforming, education, teachers, and, explore, tools]
b) Construct the document vector for Document 3 using the dictionary.
Answer: Dictionary order: students, love, studying, ai, is, transforming, education, teachers, and, explore, tools
Document 3 words: [teachers, and, students, explore, ai, tools]
Vector: [1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1]
c) Explain how Bag of Words helps in feature extraction.
Answer: Bag of Words converts text into numbers by counting word frequency. It gives vocabulary and occurrence of words, which can be used as features for machine learning models.
d) Why is the order of words not considered important in Bag of Words?
Answer: Because Bag of Words only cares about word frequency, not sequence. It treats text as a тАЬbagтАЭ of words, so meaning is captured by counts, not order.
Q. Consider the following documents :
Document 1 : AI helps humans daily.
Document 2 : Humans use AI technology.
Implement all the four steps of Bag of Words (BoW) model to create a document vector table.
Answer:
Step 1 тАУ Text PreтАСprocessing
Lowercase + tokenizing:
- Doc 1 тЖТ [ai, helps, humans, daily]
- Doc 2 тЖТ [humans, use, ai, technology]
Step 2 тАУ Create Dictionary (Vocabulary)
тАШ[ai, helps, humans, daily, use, technology]тАЩ
Step 3 тАУ Document Vectors
- Doc 1 тЖТ [1,1,1,1,0,0]
- Doc 2 тЖТ [1,0,1,0,1,1]
Step 4 тАУ Document Vector Table
| Word | ai | helps | humans | daily | use | technology |
|---|---|---|---|---|---|---|
| Document 1 | 1 | 1 | 1 | 1 | 0 | 0 |
| Document 2 | 1 | 0 | 1 | 0 | 1 | 1 |
Q. Consider the following documents:
Document 1 : Data Science requires information.
Document 2 : Information analysis requires data.
Implement all the four steps of Bag of Words (BoW) model to create a document vector table.
Answer:
Step 1 тАУ Text PreтАСprocessing
Lowercase + tokenizing:
- Doc 1 тЖТ [data, science, requires, information]
- Doc 2 тЖТ [information, analysis, requires, data]
Step 2 тАУ Create Dictionary (Vocabulary)
- тАШ[data, science, requires, information, analysis]тАЩ
Step 3 тАУ Document Vectors
- Doc 1 тЖТ [1,1,1,1,0]
- Doc 2 тЖТ [1,0,1,1,1]
Step 4 тАУ Document Vector Table
| Word | data | science | requires | information | analysis |
|---|---|---|---|---|---|
| Document 1 | 1 | 1 | 1 | 1 | 0 |
| Document 2 | 1 | 0 | 1 | 1 | 1 |
Q. You have two documents :
Document 1 : CV is an upcoming field.
Document 2 : Image Feature is an important part of CV.
Implement all four steps of the Bag of Words (BoW) model to create a document vector table. Depict the outcome of each step.
Answer:
Step 1 тАУ Text PreтАСprocessing
Lowercase + tokenizing:
- Doc 1 тЖТ [cv, is, an, upcoming, field]
- Doc 2 тЖТ [image, feature, is, an, important, part, cv]
Step 2 тАУ Create Dictionary (Vocabulary)
- тАШ[cv, is, an, upcoming, field, image, feature, important, part]тАЩ
Step 3 тАУ Document Vectors
- Doc 1 тЖТ [1,1,1,1,1,0,0,0,0]
- Doc 2 тЖТ [1,1,1,0,0,1,1,1,1]
Step 4 тАУ Document Vector Table
| Word | cv | is | an | upcoming | field | image | feature | important | part |
|---|---|---|---|---|---|---|---|---|---|
| Document 1 | 1 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 0 |
| Document 2 | 1 | 1 | 1 | 0 | 0 | 1 | 1 | 1 | 1 |
Disclaimer: We have taken an effort to provide you with the accurate handout of тАЬRevisiting AI Project Cycle & Ethical Frameworks for AI Class 10 Extra Questions and AnswersтАЬ. If you feel that there is any error or mistake, please contact me at anuraganand2017@gmail.com. The above CBSE study material present on our websites is for education purpose, not our copyrights. All the above content and Screenshot are taken from Artificial Intelligence Class 10 CBSE Textbook, Sample Paper, Old Sample Paper, Board Paper and Support Material which is present in CBSEACADEMIC website, This Textbook and Support Material are legally copyright by Central Board of Secondary Education. We are only providing a medium and helping the students to improve the performances in the examination.
Images and content shown above are the property of individual organizations and are used here for reference purposes only.
For more information, refer to the official CBSE textbooks available at cbseacademic.nic.in