~/Leveraging Linguistics and Computer Science

1.1 Understanding Human Language Complexity

Linguistics is the field of study that strategically applies linguistic principles — structure, semantics, pragmatics, sociolinguistics — to meet specific goals in marketing, advertising, education, or NLP. Understanding how language works lets you tailor messages, improve communication, and influence behaviour.

1.2 Introduction to Natural Language Processing (NLP)

Structured vs Unstructured Data

How NLP Handles "Messiness"

1.3 Three Language Elements NLP Must Identify

1.4 Emotion Detection vs Sentiment Analysis

1.5 The Classification Problem — Language Ambiguity

How AI Solves the Classification Problem

1.6 Chatbots

Two Types of Chatbots

1.7 Structure of a Chatbot — Frontend and Backend

1.8 Three Building Blocks — Intent · Entity · Dialog

1.9 The Five Phases of NLP

NLP processes human language through five sequential phases — each uses deep-neural-network ML techniques to mimic how the human brain understands language.

Phase 1 — Lexical Analysis (Tokenisation & Morphology)

Understand and examine the structure of words. Break text into paragraphs, phrases, words. Use:

• Stemming — reduces words to their root form by removing suffixes (-ing, -ly, -es, -s).
• Lemmatization — reduces words to their dictionary form, considering parts of speech.

Phase 2 — Syntactical Analysis (Parsing & Grammar)

Checks grammar, word order, word relationships. Uses dependency grammar and Part-of-Speech (POS) tags.

Phase 3 — Semantic Analysis

Understands the meaning conveyed by a sentence in a clear, contextually appropriate manner. Extracts insights to comprehend intended messages.

Phase 4 — Discourse Integration

Understands a statement's meaning based on preceding sentences. Helps interpret pronouns and proper-noun references.

Phase 5 — Pragmatic Analysis

Studies meanings in a particular situation. Recognises how individuals communicate, the context, the speaker, and many other real-world factors — "who said what to whom".

1.10 Walkthrough Example — "The cat sat on the mat"

1.11 Applications of NLP

Businesses use NLP to analyse data, discover insights, automate operations, and gain competitive advantage.

1.12 Practical — POS Tagging with NLTK

pip install nltk

import nltk
from nltk.tokenize import word_tokenize
from nltk import pos_tag

nltk.download("punkt")
nltk.download("averaged_perceptron_tagger")

sentence = "The quick brown fox jumps over the lazy dog."

# Tokenise
words = word_tokenize(sentence)

# Tag each word with its POS
pos_tags = pos_tag(words)

for word, pos in pos_tags:
    print(f"Word: {word}, POS: {pos}")

Common POS Tag Meanings

1.13 Practical — Simple Rule-Based Chatbot in Python

import random

def get_response(user_input):
    user_input = user_input.lower()
    if "hello" in user_input:
        return "Hi there! How can I assist you?"
    elif "how are you" in user_input:
        return "I'm just a bot, but thanks for asking!"
    elif "bye" in user_input:
        return "Goodbye! Have a great day!"
    else:
        return "I'm sorry, I didn't understand that."

def main():
    print("Welcome to the Simple Chatbot!")
    print("Type 'bye' to exit.")

    while True:
        user_input = input("You: ")
        if user_input.lower() == "bye":
            print("Chatbot: Goodbye! Have a great day!")
            break
        else:
            response = get_response(user_input)
            print("Chatbot:", response)

if __name__ == "__main__":
    main()

1.14 Activities & Certification (Syllabus)