CBSE Class 10 · Artificial Intelligence, code 417 · Unit 6, 2026-27

NLP class 10 questions and answers: Unit 6 written the way the examiner marks it.

These NLP class 10 questions and answers cover all of Unit 6 of CBSE 417 for 2026-27: why computers find human language hard, where NLP is used, the five stages, script bots and smart bots, and text normalisation done on a real piece of text. Each topic ends in an answer you could write in the paper, sized to its marks. In our Monday class the unit is taught this way, and the written answers are marked on screen against the scheme.

Book a free demo class Book a priority demo Ask on WhatsApp

Live online · whole Unit 6 answered · stages, chatbots, normalisation · answers marked on screen · Orange case study for the practical · first class free

Start here

Courses that teach Unit 6

The 417 course whose Class 10 batch covers this unit, the Orange course for the sentiment analysis case study the practical uses, and Python for students who want to see text processing done in code.

CBSE Computational Thinking and AI for Teens course thumbnail

The batch / 417 Class 10

CBSE AI for Class 9 to 12

Unit 6 taught in order, from features of language to TFIDF, with written answers in every mark band marked live.

Open the course →
Visual Machine Learning with Orange for Teens course thumbnail

Practical / Orange

Visual ML with Orange

The no-code sentiment analysis walkthrough the curriculum names for the NLP practical, built widget by widget.

Open the course →
Python for Teens course thumbnail

Code / Python

Python for Teens

Splitting, lowercasing and counting words in a few lines of Python, so tokens and stopwords stop being abstract.

Open the course →

Ans. The short version

NLP class 10 questions and answers for CBSE 417 come from Unit 6, Natural Language Processing, worth 8 of the 50 theory marks in 2026-27. The examined topics are: features of natural language, applications of NLP, the five stages (lexical, syntactic, semantic, discourse integration, pragmatic), script bots versus smart bots, and text processing: text normalisation, Bag of Words and TFIDF. In the 2025-26 sample paper the unit had five one-mark items, one two-mark and one four-mark question. Modern Age Coders teaches the unit live in a Monday and Wednesday 9:00 PM IST batch, or personalised one to one.

Q1. How much is NLP worth?

How many marks is NLP in Class 10 AI, and what is examined?

Natural Language Processing carries 8 of the 50 theory marks in CBSE 417 for 2026-27, the third-largest unit after Modeling (11) and Evaluating Models (10). The curriculum splits it into a theory part and a smaller practical part.

Topic in Unit 6Assessed inWhat the answer usually asks
Features of natural language, why NLP is neededTheoryTwo features, or why a computer struggles with human language
Applications of NLPTheoryName and explain two or four, with a real example
Stages of NLPTheoryName a stage from a description, or explain all five
Chatbots: script bot and smart botTheoryDifferences, or classify a given bot
Text processing: normalisation, Bag of Words, TFIDFTheoryNormalise given text, build a vector, compute TFIDF
Code and no-code NLP tools, sentiment analysis in OrangePracticalRun the case study, explain each step in the viva

The question shapes, from the last sample paper

  • Five one-mark objective items in the 2025-26 paper, with choice across the AI units.
  • One two-mark question, typically a difference or a short definition.
  • One four-mark question, often text normalisation or a TFIDF calculation on a small corpus.
  • The 2026-27 sample paper for 417 has not been published yet, so treat these counts as a guide, not a promise.

Where hours go in the syllabus

CBSE gives the unit 20 theory hours and 7 practical hours. The theory hours are spent mostly on the stages and on text processing, which is also where the longer answers come from. The practical hours go to sentiment analysis, which reaches the practical exam and the viva rather than the written paper.

The full blueprint for every unit is on the 417 exam date and paper pattern page.

Q2. What are the stages?

What are the stages of NLP in Class 10?

The five stages of NLP are lexical analysis, syntactic analysis, semantic analysis, discourse integration and pragmatic analysis, in that order. Each one checks the text at a deeper level than the one before: words, then grammar, then meaning, then the link between sentences, then the intended purpose.

StageOne-line definitionExample that passes or fails it
1. Lexical analysisBreaks a long text into paragraphs, sentences and words, and identifies each word"Rohan bought mangoes. They were sweet." becomes two sentences and their words
2. Syntactic analysis (parsing)Checks that the words follow the grammar of the language"Mangoes bought Rohan sweet were" fails: the order breaks the rules
3. Semantic analysisChecks that the grammatically correct sentence actually makes sense"The mango sang loudly" passes grammar but fails meaning
4. Discourse integrationLinks a sentence with those before and after itWorking out that "They" in the second sentence means the mangoes
5. Pragmatic analysisFinds the intended meaning in the real situation"Can you pass the salt?" is a request, not a question about ability
Model answer, 4 marksexplain the stages of NLP
NLP understands text in five stages.
1. Lexical analysis: the text is split
   into sentences and words.
2. Syntactic analysis: the sentence is
   checked against grammar rules.
3. Semantic analysis: the meaning is
   checked; "the mango sang" fails.
4. Discourse integration: each sentence
   is read with the ones around it, so
   "they" is linked to "mangoes".
5. Pragmatic analysis: the real intent
   is found; "can you pass the salt?"
   is understood as a request.

Five stages, each with one line and one example. Order matters: a jumbled list loses a mark in most schemes.

How students lose marks here

  • Mixing up syntactic and semantic. Syntax is grammar; semantics is meaning. A sentence can pass the first and fail the second, never the reverse in a useful exam example.
  • Calling discourse "the meaning". Discourse is about how sentences connect, especially pronouns like it, he and they.
  • Skipping the example. A definition alone usually earns half the marks for a stage.
  • Writing "parsing" for lexical. Parsing is the other name for syntactic analysis.

A one-mark form of the same idea: "Which stage would reject a grammatically correct sentence that makes no sense?" Answer: semantic analysis.

Q3. Applications and chatbots

Applications of NLP, and script bot vs smart bot

A chatbot is a program that holds a conversation with a person in text or speech. A script bot follows a fixed, pre-written flow; a smart bot uses NLP and machine learning to understand open questions and improves as it sees more data.

Point of differenceScript botSmart bot
How it worksFollows a script: buttons, menus or set keywordsUnderstands free text using NLP
Language processingLittle or noneLarge: intent, context and meaning
LearningDoes not learn; changes only when someone edits the scriptLearns from more data and conversations
Data it usesA small set of fixed repliesLarge databases and other resources
Building itEasy, often with no codingNeeds coding and training
ExampleA school fee bot that offers "1 for dates, 2 for receipts"A voice assistant that answers "Will I need an umbrella in Pune tomorrow?"

A two-mark question asks for two differences; four rows of this table cover a four-mark one. Write each difference as a pair, script bot first, so the examiner can tick both halves.

Applications of NLP the syllabus names

Voice assistants

Turn speech into text, find the intent and reply, such as setting an alarm when told "wake me at six".

Auto-generated captions

Speech in a video is converted to text on screen as it plays, which helps viewers with hearing loss.

Language translation

Text in one language is rewritten in another while keeping its meaning, not word by word.

Sentiment analysis

Decides whether a review or post is positive, negative or neutral. This is also the practical case study in Orange.

Text classification

Puts text into categories, such as sorting emails into spam and not spam, or news into sport and politics.

Keyword extraction

Pulls the most important words out of a long text, so a report can be tagged or summarised quickly.

Why is any of this hard for a computer? Human language is ambiguous ("I saw her duck"), the same idea can be said many ways, and it keeps changing. Those three features of natural language are a common two-mark question in their own right. Short contrasts of this kind are collected on CBSE Class 10 AI difference between questions.

Q4. Normalise this text

Text normalisation class 10: the steps, worked on real text

Text normalisation is the cleaning of a whole corpus so a machine can work with it: the text is cut into sentences and tokens, low-value words and symbols are dropped, case is made uniform and each word is reduced to a base form. Here it is done on a two-document corpus, step by step.

The corpustwo documents
Document 1:
Grandma tells the best stories at night.

Document 2:
We were listening to her stories, and
we laughed!

A corpus is the whole collection of text being processed. Normalisation works on all of it together.

  1. Sentence segmentation

    Each document here is one sentence, so the corpus gives two sentences.

  2. Tokenisation

    Every word and every punctuation mark becomes a token. Document 1 gives 8 tokens (7 words and the full stop); Document 2 gives 11 (9 words, a comma and an exclamation mark). 19 tokens in all.

  3. Removing stopwords and special characters

    Dropping the, at, we, were, to, her, and, and all punctuation leaves "Grandma tells best stories night" and "listening stories laughed".

  4. Converting to a common case

    Everything becomes lower case, so "Grandma" and "grandma" can never be counted as two different words.

  5. Stemming or lemmatisation

    Each word is cut to its base: tells to tell, listening to listen, laughed to laugh, stories to story (lemma). The result: grandma, tell, best, story, night, listen, laugh, 7 unique words.

WordAfter stemmingAfter lemmatisationWhat it shows
storiesstoristoryA stem need not be a real word; a lemma always is
listeninglistenlistenBoth methods agree when the suffix is regular
betterbettergoodOnly lemmatisation knows the dictionary root
happilyhappilihappyRules chop endings without checking the result is English

Stemming against lemmatisation, in one answer

Stemming removes affixes by rule, so it is fast but may leave a word that does not exist. Lemmatisation finds the proper dictionary form, so it is slower but always gives a meaningful word. The usual exam choice: lemmatisation when meaning matters, stemming when speed matters.

What comes next: Bag of Words and TFIDF

The 7 normalised words become the dictionary for Bag of Words, and each document becomes a row of counts. TFIDF then scores every word by how special it is to one document. The complete worked tables, three documents from raw text to final TFIDF values, are on Bag of Words and TFIDF for Class 10 AI.

Q5. Practise by mark band

NLP class 10 questions and answers, by marks

Original questions in the shapes the paper uses. Try each before opening the answer. The one-mark answers are short on purpose; the two- and four-mark ones show the length the scheme rewards.

One mark each

  1. Which stage of NLP works out that "she" in the second sentence refers to Asha in the first?
    Answer Discourse integration, which links each sentence with its neighbours.
  2. How many tokens are there in "Is it raining? Take an umbrella, Riya."?
    Answer 10: seven words plus the question mark, the comma and the full stop.
  3. Words such as "is", "an" and "the" that are removed because they add little meaning are called
    Answer Stopwords.
  4. A bank's chatbot only lets you tap one of four buttons. Is it a script bot or a smart bot?
    Answer A script bot: it follows a fixed flow and understands no free text.
  5. Name the NLP application that turns spoken words in a video into text on screen.
    Answer Auto-generated captions.
  6. "Doctors said the new medicine works. It works fast!" How many tokens?
    Answer 11: nine words, the full stop and the exclamation mark. "works" counts twice because tokens are not unique words.
  7. Which gives a meaningful base word: stemming or lemmatisation?
    Answer Lemmatisation.
  8. What is the whole body of text taken from all the documents together called?
    Answer The corpus.

Two marks each

  1. Give two differences between a script bot and a smart bot.
    Answer A script bot follows a pre-written script and has little language processing, while a smart bot understands free text using NLP. A script bot does not learn, while a smart bot improves with more data.
  2. Differentiate between syntactic and semantic analysis with an example.
    Answer Syntactic analysis checks grammar; semantic analysis checks meaning. "The mango sang loudly" is grammatically correct, so it passes the syntactic stage, but it makes no sense, so it fails the semantic stage.
  3. Why is text converted to a common case during normalisation?
    Answer A machine treats "School" and "school" as different words because their characters differ. Lowercasing everything makes them one word, so counts and vectors are correct.
  4. State any two features of natural language that make NLP difficult.
    Answer It is ambiguous: one sentence can have more than one meaning. It is redundant and changing: the same idea can be said in many ways, and words and usage change over time.

Four marks each

  1. Explain any four applications of NLP with one example each.
    Answer Voice assistants turn speech into an action, such as setting an alarm. Translation rewrites text in another language, such as a Hindi sign read in English. Sentiment analysis labels a review positive or negative, such as rating feedback on a product. Text classification sorts text into groups, such as moving spam out of the inbox.
  2. Normalise "Riya plays football. Her brothers play cricket!" Treat "her" as the only stopword. Show each step and give the final dictionary.
    Answer Segmentation: two sentences. Tokenisation: 9 tokens, seven words plus the full stop and the exclamation mark. Remove "Her" and both punctuation marks. Lower case: riya plays football / brothers play cricket. Lemmatise: plays to play, brothers to brother. Dictionary of unique words: riya, play, football, brother, cricket, so 5 words.

More objective items for this unit sit with every other unit on Class 10 AI MCQ with answers, and the spoken versions of these questions are on CBSE Class 10 AI viva questions.

Q6. How is Unit 6 taught?

Natural language processing class 10 notes become marks in the live batch

Notes tell a student what NLP is. Marks come from writing the stages in order, sizing an answer to its marks and counting tokens without slips. That is the work the class does each week.

Taught on real sentences

Each stage is shown on a sentence the class suggests, then broken on purpose: a jumbled one for syntax, a silly one for semantics, a pronoun puzzle for discourse. Students remember the stage by the sentence that failed it.

Answers marked against the scheme

Two- and four-mark answers are written in the last part of the Monday class, then shared and marked on screen point by point. A missing example or a stage out of order is caught before it becomes a habit.

The practical in Orange

On Wednesday the sentiment analysis walkthrough is built live in Orange: load reviews, preprocess, score and read the result. Students rehearse explaining each widget, because that is what the viva asks.

The no-code tool itself has its own page, Orange Data Mining for Class 10 AI. The neighbouring theory unit, worth 4 marks, is answered the same way on computer vision class 10 questions and answers.

Batch or personalised: you choose

Learn Unit 6 in the Monday and Wednesday batch, or one to one

The batch takes NLP in its place in the syllabus, with classmates whose answers you see marked beside yours. One to one starts wherever your child is stuck, whether that is the stages or a TFIDF table. Billed monthly, no admission fee, and you can stop at the end of any month.

Option 1 · Fixed batch timings

Group batch, Monday and Wednesday 9 PM

₹1,499

per month, two live classes a week

  • Monday and Wednesday, 9:00 PM IST, live on video
  • Fifteen to twenty Class 10 AI students with one teacher
  • Stages, chatbots and normalisation taught in order
  • Written NLP answers marked on screen every week
  • Orange sentiment case study built in class
Book a free demo in this batch

Option 2 · Choose your own timing

Personalised one to one

₹4,999

per month, one private class a week, at a time set with you

  • A day and hour you choose, in your own time zone
  • Starts from the NLP topic your child finds hardest
  • Normalisation and TFIDF repeated on fresh text until steady
  • Every four-mark answer read and corrected one to one
  • Same CBSE 417 syllabus and the same teachers
Ask for a personalised plan

If Unit 6 is the only weak spot, a handful of one to one sessions on the stages and text processing is usually enough. If the student has not reached NLP yet, or is behind on several units, the batch covers the whole syllabus in order. Fees appear in your own currency.

Studying outside India?

NLP classes for CBSE Class 10 students outside India

CBSE schools in the Gulf and East Africa sit the same 417 paper, with the same 8 marks for Natural Language Processing. These are the batch times in local terms this winter.

Where you liveMon and Wed 9:00 PM ISTBest format
India (IST)
every Indian city		9:00 PMBatch fits
UAE and Oman
Dubai, Abu Dhabi, Sharjah, Muscat		7:30 PMBatch fits
Saudi Arabia, Qatar, Kuwait, Bahrain
Riyadh, Jeddah, Dammam, Doha, Kuwait City, Manama		6:30 PMBatch fits
Nepal
Kathmandu		9:15 PMBatch fits
Ethiopia and East Africa
Addis Ababa and East Africa Time		6:30 PMBatch fits
Singapore and Malaysia
Singapore, Kuala Lumpur		11:30 PMChoose 1-on-1

Where the 9:00 PM IST batch falls too late, personalised one to one runs at a local hour you choose. More on studying from abroad is on CBSE Class 10 AI online classes in the Gulf and abroad.

What families say

Rated 4.9 across 547 Google reviews

Real reviews from real families. We neither write nor commission them.

★★★★★

"The one step solution for my son. Modern Age Coders make learning coding so simple that kids love it. The teachers explain complex concepts clearly with practical exercises and interactive content."

Ria Mukherjee

Parent

★★★★★

"Modern Age Coders has been a game-changer for me. I struggled to grasp IT concepts and coding before joining, but their classes transformed everything. I can now confidently write complex programs with ease."

Samriddha Mondal

Student

★★★★★

"One of the most wonderful education centres out there. Education is not limited to school syllabus but focuses on skill development."

Vansh Agarwal

Student

★★★★★

"My child Dhairya is really enjoying the Modern Age Coders classes. This is his first online class and he eagerly looks forward to it. I can already see his improvement, and the teachers are very cooperative."

Sonam Oswal

Parent of Dhairya

★★★★★

"Modern Age Coders have wonderful teachers who teach in a clear, easy and practical way. The teacher boosts students' confidence and inspires them to learn without hesitation."

Sonu Goyal

Parent

★★★★★

"I highly recommend this computer coding class! The teachers are incredibly knowledgeable and passionate about coding."

Ritu Kedia

Parent

The rest of the Class 10 series

More pages for Class 10 board students

Every page in the CBSE Class 10 AI (417) series, grouped by what you need: classes, each unit, question practice, notes and revision, and the exam itself.

Classes, tuition and batches

Unit by unit

Questions and practice

Notes and revision

Exam, marks and practicals

Choosing the subject

ICSE Class 10 Computer Applications (Java): The Tue and Wed ICSE Java batch ICSE Computer Applications syllabus ICSE Java programs practice ICSE CA important questions

Questions about NLP in Class 10 AI

NLP class 10: what students and parents ask

What are the important NLP class 10 questions and answers for 2026-27?

The questions that recur are: the five stages of NLP with examples, differences between a script bot and a smart bot, four applications of NLP, the steps of text normalisation on given text, stemming against lemmatisation, and a Bag of Words or TFIDF calculation on a small corpus. This page answers each of them in the length the marks deserve.

How many marks is NLP in CBSE Class 10 AI?

Unit 6, Natural Language Processing, carries 8 of the 50 theory marks in CBSE 417 for 2026-27. In the 2025-26 sample paper it appeared as five one-mark objective items, one two-mark question and one four-mark question, with choice across units. The sentiment analysis case study is assessed in the practical instead.

What are the stages of NLP class 10?

There are five: lexical analysis splits text into sentences and words; syntactic analysis checks grammar; semantic analysis checks meaning; discourse integration links each sentence with those around it; pragmatic analysis finds the real intent. Learn them in this order with one example each.

What is the difference between a script bot and a smart bot?

A script bot follows a fixed, pre-written flow, has little or no language processing, does not learn and is easy to build. A smart bot uses NLP to understand free text, learns from more data, works with large databases and needs coding. A menu-based fee bot is a script bot; a voice assistant is a smart bot.

What are the steps of text normalisation in class 10?

Sentence segmentation, tokenisation, removing stopwords and special characters, converting to a common case, and stemming or lemmatisation. The output is a clean list of base words for the whole corpus, which then becomes the dictionary for Bag of Words. In a four-mark answer, show the text after every step, not just the final list, because each step usually carries its own share of the marks.

What are the applications of NLP for class 10?

The curriculum names voice assistants, auto-generated captions, language translation, sentiment analysis, text classification and keyword extraction. For a four-mark answer, explain four of them with one real example each, such as spam filtering for text classification. Sentiment analysis is worth knowing best, because it is also the case study you build in Orange for the practical.

Are punctuation marks counted as tokens?

Yes. In tokenisation every word, number and special character, including commas, full stops and exclamation marks, becomes a separate token. Punctuation is only removed in the next step, along with stopwords. Most token-count mistakes come from forgetting this. So "Stop, Riya!" is four tokens: two words, a comma and an exclamation mark.

Where can I find natural language processing class 10 notes?

This page works as exam-focused notes for the whole unit: the marks, the stages table, chatbots, applications and a worked normalisation. For notes on every unit of 417 in one place, see our Class 10 AI notes page, and the CBSE handbook remains the base text.

Is TFIDF in the Class 10 AI theory paper?

Yes. TFIDF is listed under text processing in the theory part of Unit 6 for 2026-27, alongside Bag of Words and text normalisation. A small corpus calculation is a natural four-mark question, which is why we give it a page of its own with full tables.

Is sentiment analysis asked in the written paper?

As an application of NLP, yes: you may be asked what it is or for an example. The hands-on sentiment analysis case study in Orange is listed under the practical part of Unit 6, so it is assessed through the practical exam and viva rather than written out in full.

Do you teach NLP separately or as part of the whole course?

Both are possible. In the batch, NLP is taught in its place in the 417 syllabus, with written answers and the Orange case study. One to one can focus only on Unit 6 if that is the gap. Both are covered by the monthly fee shown on this page, and the first class is a free demo.

Start

Try a free NLP class with a teacher

In the free first class your child normalises a short piece of text with the teacher, names the stage each broken sentence fails, and writes one two-mark answer that is marked on screen. Afterwards the mentor tells you which parts of Unit 6 are solid and which need work, and whether the batch or one to one would suit your child better.

Want every unit summarised first? Start with CBSE Class 10 AI notes.

WhatsApp us · +91 91233 66161 · connect@modernagecoders.com

Every class is live video. The form requests a callback and reserves nothing.

We call within a few hours. No card, no enrolment fee.

Want it sooner? Book a priority demo

A full live class of about 45 to 60 minutes at a slot you pick, with a written skill report and learning roadmap on WhatsApp afterwards. The fee is adjusted against your first month if you enrol.

Book a priority demo

Keep exploring Modern Age Coders

By class and age

Learn more

Free resources

From the blog

Start here