Class 10 AI Unit 6: Natural Language Processing
20 theory hours · 7 practical hours · 8 theory marks
What this unit is about
NLP lets computers work with human language. The unit covers why natural language is hard for machines, applications (voice assistants, translation, sentiment analysis), the stages of NLP, script bots vs smart bots, text normalisation (tokenisation, stop words, stemming, lemmatization), Bag of Words and TF-IDF.
Learn it with the AI tutor, one minute each
What the unit covers
- Features of natural languages and why machines need NLP to understand them.
- Applications: voice assistants, auto translation, sentiment analysis, text classification, keyword extraction.
- Stages of NLP (lexicon, syntax, semantics), and script bots vs smart bots.
- Text normalisation, Bag of Words and TF-IDF; sentiment analysis in Orange (practical).
Key terms
- Tokenisation
- Splitting a sentence into words or symbols (tokens).
- Stop words
- Very common words (a, the, is) removed because they add little meaning.
- Stemming vs lemmatization
- Stemming chops endings and may leave a non-word (studies → studi); lemmatization returns a real word (studies → study).
- Bag of Words
- Represents text as counts of each word, ignoring word order.
- TF-IDF
- Term frequency × inverse document frequency: high for words common in one document but rare across the rest.
Exam-style questions
1. Give one difference between a script bot and a smart bot.
Show answer →
A script bot follows a fixed script and fails outside it; a smart bot uses AI to understand varied questions and improves with data.
2. List the steps of text normalisation.
Show answer →
Sentence segmentation, tokenisation, removing stop words, special characters and numbers, converting to a common case, then stemming or lemmatization.
3. Why does a word like "the" get a low TF-IDF score?
Show answer →
It appears in almost every document, so its inverse document frequency is close to zero.
Sources
Unit names, hours and marks checked against the official CBSE 2026-27 curriculum on 1 November 2026. Explanations and questions are written by CogniGuru.