CBSE Class 10 · Artificial Intelligence · board exam 2027
Chapter 6: Natural Language Processing — notes
The chapter’s 6 parts in the book’s order — the first idea of each and the points Medha Ma’am writes on the board — and the summary at the end. The full lesson and a check question for each part are in the app.
1. What is Natural Language Processing?
Okay, so, let's talk about natural language.
- • Natural language = human language (French, English, etc.)
- • Computer language = Python, C++, Java, HTML
- • Computers process only binary signals
- • NLP = AI sub-field: computers understand human language
- • Purpose: communication between computers and humans
2. Applications of NLP
Okay, so NLP is already a part of your daily life, in many ways.
- • Autogenerated captions - speech to text
- • Voice assistants - Hey Google, Alexa, Siri
- • Language Translation - Google Translate
- • Sentiment Analysis - positive/negative/neutral
- • Text Classification - sorts into categories
- • Keyword Extraction - pulls out important words
3. The Stages of NLP
Okay, so NLP doesn't understand language all at once.
- • 1. Lexical Analysis - structure of words
- • 2. Syntactic Analysis - checks grammar
- • 3. Semantic Analysis - checks meaning
- • 4. Discourse Integration - story/flow of sentences
- • 5. Pragmatic Analysis - intended real-world meaning
4. Text Normalisation
Okay, so computers only understand numbers.
- • Corpus = all text from all documents
- • 1. Sentence Segmentation 2. Tokenization
- • 3. Remove stop words, special characters, numbers
- • 4. Convert to common case (lowercase)
- • 5. Stemming: healed -> heal, studies -> studi
- • 6. Lemmatization: studies -> study (meaningful, slower)
5. Bag of Words
Okay, so once our text is normalised into tokens, we need to turn those tokens into numbers.
- • Bag of Words: gives 1) vocabulary 2) word frequency
- • 'Bag' = order does not matter
- • Steps: process text, dictionary, document vectors
- • Doc1: Aman and Avni are stressed
- • Dictionary: aman, and, avni, are, stressed, went, to, a, ...
- • Doc1 vector: 1 1 1 1 1 0 0 0 0 0 0 0
6. TFIDF
Okay, so let's talk about TFIDF.
- • TF = frequency of a word in one document
- • IDF = total documents / document frequency
- • TFIDF(W) = TF(W) * log( IDF(W) )
- • and: 10/10 = 1, log(1) = 0
- • pollution: 10/3 = 3.3333, log = 0.522
- • Uses: classification, topic modelling, retrieval, stop word filtering
Summary
Okay, so let's quickly go over everything we covered today. We started with Natural Language Processing — that's the sub-field of AI that helps computers understand human languages. Why do we need it? Because computers only process binary signals, and human languages are complex, and they depend on context. We looked at real uses of NLP too — autogenerated captions, voice assistants, language translation, sentiment analysis, text classification and keyword extraction. Then you learned the five stages of NLP, and the order matters here. It goes Lexical Analysis, then Syntactic Analysis, then Semantic Analysis, then Discourse Integration, and finally Pragmatic Analysis. After that came Text Normalisation. This simplifies a corpus, and it does this through sentence segmentation, tokenization, stop word removal, changing everything to a common case, stemming and lemmatization. Next, we saw Bag of Words — it takes those normalised tokens and turns them into a vocabulary, and then into document vectors showing word frequencies. And finally, there was TFIDF. You worked it out as TFIDF(W) = TF(W) times log( IDF(W) ). This gives a low value to words that appear in every document, and a high value to words that are frequent in one document but rare across the whole corpus. That's a lot of ground we've covered. Which of these five NLP stages do you think happens first when you read a sentence yourself?
AskMedha · Medha Ma’am — CBSE Class 10 Artificial Intelligence, Chapter 6. Written from the textbook, checked twice.
Questions parents and students ask
- How do I get the "Natural Language Processing" notes as a PDF?
- Press "Save as PDF" — the phone’s print sheet opens; choose "Save as PDF" there. The PDF holds the notes only.
- Where are these notes written from?
- From the chapter’s own textbook text, part by part, in the book’s own terms; a second, independent model then checked every part against the book. The full lesson, a check question for each part and the practice are in the AskMedha app.
The same preparation, with Medha Ma’am — on your phone
Every question of every chapter with its model answer, practice questions in the board’s own shapes, 60 minutes of class a day, written answers marked, a test every Sunday and a WhatsApp report to parents.
Medha Ma’am is an AI teacher, not a live tutor. Every answer is checked twice; a person takes responsibility.