Chapter 6: Natural Language Processing

Important questions — the ones the board asked most (13)

1. Q1Short answer4 marksAsked: 2026

   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.

   

   Medha Ma’am

   AskMedha’s AI teacher

   Hear it from Medha Ma’am · 135 s

   Model answer · Bag of Words model, document vector table

   1. 1.Step 1 – Text normalisation (lowercase, punctuation removed): Document 1 → [data, science, requires, information]; Document 2 → [information, analysis, requires, data].1 mark
   2. 2.Step 2 – Dictionary of unique words: data, science, requires, information, analysis.1 mark
   3. 3.Step 3 – Document vectors (in the dictionary's order): Document 1 = 1, 1, 1, 1, 0; Document 2 = 1, 0, 1, 1, 1.1 mark
   4. 4.Step 4 – Document vector table: columns data | science | requires | information | analysis; Document 1: 1 | 1 | 1 | 1 | 0; Document 2: 1 | 0 | 1 | 1 | 1.1 mark

   Diagram: Draw the final document vector table with the header row as the vocabulary words (data, science, requires, information, analysis) and two rows below labelled Document 1 and Document 2, filled with the 1s and 0s as calculated.

   Marks split from a structure derived from past papers (checked twice); not CBSE’s official scheme

2. Q2Short answer4 marksAsked: 2025

   Consider the following documents : Document 1 : NLP is a domain of AI. Document 2 : NLP stands for Natural Language Processing. Implement all the four steps of Bag of Words (BoW) model to create a document vector table.

   

   Medha Ma’am

   AskMedha’s AI teacher

   Hear it from Medha Ma’am · 130 s

   Model answer · Bag of Words document vectors

   1. 1.Step 1 – Text Normalisation (collecting data and pre-processing it): The corpus has two documents. Each sentence is split into tokens, the full stop (a special character) is removed and the whole text is converted to lowercase. Document 1: [nlp, is, a, domain, of, ai] Document 2: [nlp, stands, for, natural, language, processing]1 mark
   2. 2.Step 2 – Create a Dictionary: Make a list of all the unique words occurring in the corpus (the vocabulary). The word "nlp" appears in both documents, but it is written only once. Dictionary: nlp, is, a, domain, of, ai, stands, for, natural, language, processing (11 unique words)1 mark
   3. 3.Step 3 – Create a document vector: Write the vocabulary in the top row. For each word in a document that matches the vocabulary, put a 1 under it. If the same word appears again, increase the value by 1. If a word does not occur in that document, put a 0 under it. Document 1 vector: 1 1 1 1 1 1 0 0 0 0 0 Step 4 – Create document vectors for all the documents and put them together to get the document vector table: Word | nlp | is | a | domain | of | ai | stands | for | natural | language | processing Document 1 | 1 | 1 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 Document 2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 1 | 1 | 1 The header row holds the vocabulary of the corpus, and each of the other rows is the document vector of one document.2 marks

   • Show the tokens of both documents in lowercase after Text Normalisation.
   • Write "nlp" only once in the Dictionary, because it lists only unique words.
   • Give the full document vector table, with the vocabulary in the header row and one row of 0s and 1s for each document.

   Marks split as in the board’s published marking scheme

3. Q3Long answer4 marksAsked: 2024

   19. Consider the following two documents : Document 1 : ML and DL are part of AI. Document 2 : DL is a subset of ML. Implement all four steps of the Bag of Words (BoW) model to create a document vector table. Depict the outcome of each step.

   

   Medha Ma’am

   AskMedha’s AI teacher

   Hear it from Medha Ma’am · 140 s

   Model answer · Bag of Words model, document vector table

   1. 1.Step 1 – Tokenisation (after lowercasing): Document 1 → ml, and, dl, are, part, of, ai; Document 2 → dl, is, a, subset, of, ml.1 mark
   2. 2.Step 2 – Vocabulary of unique words: ml, and, dl, are, part, of, ai, is, a, subset.1 mark
   3. 3.Step 3 – Frequency in each document: Document 1 has ml, and, dl, are, part, of, ai once each and is, a, subset 0; Document 2 has dl, is, a, subset, of, ml once each and the rest 0.1 mark
   4. 4.Step 4 – Document vector table (columns ml, and, dl, are, part, of, ai, is, a, subset): D1 = 1 1 1 1 1 1 1 0 0 0; D2 = 1 0 1 0 0 1 0 1 1 1.1 mark

   Diagram: Draw the final document vector table with the vocabulary words (ml, and, dl, are, part, of, ai, is, a, subset) as column headers in the top row, and two rows labelled Document 1 and Document 2 below, filled with 1s and 0s showing the frequency count of each word in each document.

   Marks split from a structure derived from past papers (checked twice); not CBSE’s official scheme

4. Q4Long answer4 marksAsked: 2023

   Create a document vector table from the following documents by implementing all the four steps of Bag of words model. Also depict the outcome of each step. Document 1 : Sameera and Sanya are classmates. Document 2 : Sameera likes dancing but Sanya loves to study mathematics.

   How the model answer begins

   1. Step 1 – Tokenisation: Document 1 → Sameera, and, Sanya, are, classmates; Document 2 → Sameera, likes, dancing, but, Sanya, loves, to, study, mathematics.

   The full answer from Medha Ma’am →
5. Q5Very short answer2 marksAsked: 2026

   How is Stemming different from Lemmatization ? Explain how the word "Wolves" would be processed by stemming and lemmatization.

   How the model answer begins

   1. Stemming and lemmatization both remove the affixes of words. Stemming: the stemmed word may not be meaningful, because it only removes the affixes, so it is faster. Lemmatization: the word we get after affix removal…

   The full answer from Medha Ma’am →
6. Q6Short answer2 marksAsked: 2025

   What is the primary difference between Human Language and Computer Language ?

   How the model answer begins

   1. A natural language is a human language, such as French, Spanish, English, Japanese, etc. Human language is natural and in it, a word can have multiple meanings and the meanings fit into the statement according to the…

   The full answer from Medha Ma’am →
7. Q7Short answer2 marksAsked: 2024

   12. What are the primary differences between Script-bots and Smart-bots ?

   How the model answer begins

   1. Script-bots follow a fixed set of pre-defined rules and instructions. They are scripted or in other words are traditional chatbots, and because they work on a fixed set of rules, they are simple and work for a platform…

   The full answer from Medha Ma’am →
8. Q8Short answer2 marksAsked: 2023

   Define Chatbot. What are its types ?

   How the model answer begins

   1. A chatbot is a computer program that's designed to simulate human conversation through voice commands or text chats or both. It can learn over time how to best interact with humans. It can answer questions and…

   The full answer from Medha Ma’am →
9. Q9Short answer2 marksAsked: 2023

   With reference to data processing, expand the term TFIDF. Also give any two applications of TFIDF.

   How the model answer begins

   1. TFIDF stands for Term Frequency and Inverse Document Frequency. TFIDF helps us identify the value of each word.

   The full answer from Medha Ma’am →
10. Q10Very short answer1 markAsked: 2023

    ________ helps to find the best model that represents our data and how well the chosen model will work in future.

    How the model answer begins

    1. Evaluation helps to find the best model that represents our data and how well the chosen model will work in future.

    The full answer from Medha Ma’am →
11. Q11Very short answer1 markAsked: 2023

    ________ is a term used for any word or number or special character occurring in a sentence. (Token / Punctuator)

    How the model answer begins

    1. Token is the term used for any word or number or special character occurring in a sentence.

    The full answer from Medha Ma’am →
12. Q12Very short answer1 markAsked: 2023

    When the prediction matches the reality, the condition is termed as ________.

    How the model answer begins

    1. True Positive (or True Negative) — the prediction matches the reality.

    The full answer from Medha Ma’am →
13. Q13Very short answer1 markAsked: 2025

    Which type of chat-bot has a wide functionality, is flexible and powerful, and works on bigger databases directly ?

    How the model answer begins

    1. A Smart-bot (an AI-based chatbot) — it is flexible and powerful, has wide functionality and works on bigger databases directly.

    The full answer from Medha Ma’am →

Objective questions with the board’s key (10)

1. 1. CBSE 2026

   Which type of chat bot requires coding and works on bigger databases directly ?

   • (A) Script bot
   • (B) Smart bot ✓
   • (C) Traditional bot
   • (D) Rule-based bot

   Answer: (B)

2. 2. CBSE 2026

   Assertion (A) : Converting text to lowercase is preferable in text preprocessing. Reason (R) : It ensures that “Hello” and “hello” are treated as the same word by the machine.

   • (A) Both (A) and (R) are true and (R) is the correct explanation of ✓
   • (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)

3. 3. CBSE 2026

   A company wants to analyze 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)

4. 4. CBSE 2025

   (v) Which application of NLP helps to provide an overview of a news item or blog post ? It also avoids redundancy from multiple sources and maximises the diversity of content obtained. (vi) Which condition of evaluation does the following diagram indicate ? Prediction : No Reality : Yes

   • (A) Virtual Assistants
   • (B) Sentiment Analysis
   • (C) Text Classification
   • (D) Automatic Summarization ✓

   Answer: (D)

5. 5. CBSE 2025

   A corpus contains 4 documents in which the words such as ‘an, is, the’ were appearing frequently. Identify the term that is used for such words.

   • (A) Stop word ✓
   • (B) Rare word
   • (C) Missing word
   • (D) Removable word

   Answer: (A)

6. 6. CBSE 2025

   Which application of NLP helps to provide an overview of a news item or blog post ? It also avoids redundancy from multiple sources and maximises the diversity of content obtained.

   • (A) Virtual Assistants
   • (B) Sentiment Analysis
   • (C) Text Classification
   • (D) Automatic Summarization ✓

   Answer: (D)

7. 7. CBSE 2025

   Which of the following applications of NLP (Natural Language Processing) is associated with spam filtering in e-mails ?

   • (A) Virtual Assistants
   • (B) Sentiment Analysis
   • (C) Text Classification ✓
   • (D) Automatic Summarization

   Answer: (C)

8. 8. CBSE 2025

   In the context of NLP, which of the following words represents a stem resulting from stemming for “Studies” ?

   • (A) Study
   • (B) Stud
   • (C) Studi ✓
   • (D) Studied

   Answer: (C)

9. 9. CBSE 2023

   Email filters, spam filters, smart assistants are the examples of :

   • (A) Pocket Assistants
   • (B) CV
   • (C) NLP ✓
   • (D) Evaluation

   Answer: (C)

10. 10. CBSE 2023

    Select the correct features of Smart Bot :

    • (A) Smart-bots are flexible and powerful
    • (B) Coding is required to take this up on board
    • (C) Smart bots work on bigger databases and other resources directly
    • (D) All of the above ✓

    Answer: (D)

Questions parents and students ask

How many marks does "Natural Language Processing" carry in CBSE Class 10 Artificial Intelligence?

In the CBSE papers of 2023–2026, this chapter carried about 7 marks and about 7 questions a year; by marks it ranks 3 in Artificial Intelligence.

Which are the most important (VVI) questions of "Natural Language Processing"?

The 13 questions above are from the board’s real papers, each with the years it was asked; the most-asked come first with their full model answers. All 13 written questions of this chapter, with answers, are in the AskMedha app.

Do the answers follow the board’s marking scheme?

Yes. CBSE publishes its marking schemes; every model answer here is written point by point to the marks the board’s own scheme gives, and checked by a second, independent model.