Unit 7: Leveraging Linguistics & Computer ScienceHuman Language Ambiguity, Chatbots & The Five Phases of NLP
The comprehensive CBSE Class 11 guide for Unit 7. Understand why human language is messy, explore Groucho Marx joke decomposition (Tokens, Entities, Relationships, Concepts), compare Rule-based vs. AI-powered Chatbots, master the Five Phases of NLP, and practice official handbook MCQs.
1. Understanding Human Language Complexity & Ambiguity
Computers are built for structured, clean binary data. In contrast, human natural language is unstructured, inherently messy, and full of ambiguity. Classic language riddles like "Why does your nose run and your feet smell?" or phrases like "shipping a box by train" create classification challenges because identical words carry wildly different contextual semantics.
"One morning I shot an elephant in my pajamas. How he got in my pajamas, I don't know."
I, elephant, pajamasI + elephant, I + pajamas, elephant + pajamasSafari, Rifle, Photographed| Dimension | Emotion Detection | Sentiment Analysis |
|---|---|---|
| Definition | Identifies distinct human emotion categories (anger, joy, sadness) | Measures polarity and strength of emotion on a sliding scale |
| Output | Discrete emotion labels | Positive, Negative, or Neutral scores |
| Use Cases | Customer feedback emotion triggers, psychological assessments | Product review monitoring, brand sentiment tracking on social media |
2. Chatbot Architecture: Intents, Entities & Dialog Trees
Messaging Interface
Serves as the client-side communication channel (web chat widget, mobile app UI, WhatsApp bot). Lacks deep contextual reasoning on its own.
Logic & Dialog Memory
Processes user utterances, extracts intents and entities, queries internal databases/knowledge graphs, and maintains session context across dialogue turns.
Key Chatbot Concepts:
CheckOperatingHours, OrderIceCream).Location: Bangalore, Flavor: Chocolate).3. The Five Sequential Phases of NLP
1. Lexical Analysis
Tokenization & Base FormsBreaks raw text into paragraphs, sentences, and tokens. Applies lexical normalization: Stemming (removing affixes like -ing, -ly) and Lemmatization (reducing words to dictionary base forms using POS tags).
2. Syntactical Analysis
Grammar & Parse TreesChecks grammar, word layout, and structural relationships. Constructs a Syntax Tree (Parse Tree) and assigns Part of Speech (POS) tags. Rejects nonsensical lines like 'Mumbai travels to Anuj'.
3. Semantic Analysis
Literal Meaning ExtractionExamines the literal, contextually valid meaning conveyed by a sentence. Distinguishes logical statements from syntactically correct but meaningless phrases (e.g. 'colorless green ideas sleep furiously').
4. Discourse Integration
Context & Pronoun ResolutionInterprets statements based on preceding dialogue or text. Resolves ambiguous pronoun references like 'it', 'he', or 'she' by linking them to earlier mentioned entities (e.g., 'Arti wants it').
5. Pragmatic Analysis
Real-World Situational IntentThe deepest level of NLP. Explores 'who said what to whom', interpreting sarcasm, metaphors, humor, and social communication rules in specific real-world cultural environments.
Official Handbook MCQs & Answer Key
Click any option to instantly see if you're correct with the official CBSE explanation.
Which of the following is NOT a common task within Natural Language Processing (NLP)?
What is the primary linguistic challenge faced by Natural Language Processing systems?
What is a Chatbot in modern computing?
Which of the following application areas is powered primarily by Natural Language Processing?
Which of the following statements about Voice Recognition Interfaces (e.g. Siri, Alexa) is true?
Unit 7 Quick Recall Cheat Sheet
Frequently Asked Questions (FAQ)
Build Intelligent Chatbots with 1:1 Live Mentorship
Master text tokenization, sentiment analysis, and chatbot development on Dialogflow and Python. Get 1-on-1 personalized guidance from certified NLP specialists to score top marks in Class 11 AI.