ScholarQuill logoScholarQuillUniversity Notes
  • Notes
  • Past Papers
  • Blogs
  • Todo
Login
ScholarQuill logoScholarQuillUniversity Notes
Login
NotesPast PapersBlogsTodo
More
SubjectsDiscussionCGPA CalculatorGPA CalculatorStudent PortalCourse Outline
About
About usPrivacy PolicyReportContact
Notes
Past Papers
Blogs
Todo
Analytics
    Current Subject
    🧩
    Artificial Intelligence
    COMP2121
    Progress0 / 19 topics
    Topics
    1. An Introduction to Artificial Intelligence and its applications towards Knowledge Based Systems2. Introduction to Reasoning and Knowledge Representation3. Problem Solving by Searching: Informed searching4. Problem Solving by Searching: Uninformed searching5. Heuristics in Problem Solving6. Local searching algorithms7. Minimax algorithm8. Alpha-beta pruning9. Game-playing in AI10. Case Study: General Problem Solver11. Case Study: ELIZA12. Case Study: Student13. Case Study: Macsyma14. Learning from examples15. Artificial Neural Networks (ANN)16. Natural Language Processing17. Recent trends and applications of AI algorithms18. Python programming for AI19. Implementation of AI techniques in Python
    COMP2121›Natural Language Processing
    Artificial IntelligenceTopic 16 of 19Regular Notes

    Natural Language Processing

    2 minread
    384words
    Beginnerlevel

    🌐 Natural Language Processing (NLP)

    Natural Language Processing (NLP) is a subfield of Artificial Intelligence (AI) that focuses on enabling computers to understand, interpret, generate, and interact with human languages like English, Hindi, or any spoken/written language.


    🧠 Why NLP?

    Humans communicate using natural language, but computers work with numbers and structured data. NLP bridges the gap between human language and machine understanding, allowing AI systems to:

    • Read and understand text
    • Respond to human queries
    • Translate between languages
    • Summarize or generate content

    🔧 Key Tasks in NLP

    Task What it Does Example
    Tokenization Breaks text into words or sentences "Hello, world!" → ["Hello", ",", "world", "!"]
    Part-of-Speech Tagging Identifies grammatical parts of speech "dog" → noun, "run" → verb
    Named Entity Recognition (NER) Identifies entities like names, locations, etc. "John lives in Paris" → ["John" → person, "Paris" → location]
    Sentiment Analysis Detects sentiment or emotion "I love this movie!" → Positive
    Machine Translation Translates between languages "Bonjour" → "Hello"
    Text Summarization Produces a shorter version of a document Long article → Short summary
    Question Answering Finds answers from text or databases "Who is the president of the USA?"
    Speech Recognition Converts spoken language to text Audio → Text

    ⚙️ How NLP Works

    1. Text Preprocessing:

      • Clean and prepare the text.
      • Involves steps like tokenization, stemming, lemmatization, stop-word removal.
    2. Feature Extraction:

      • Convert text to numbers using methods like:

        • Bag of Words
        • TF-IDF (Term Frequency - Inverse Document Frequency)
        • Word Embeddings (e.g., Word2Vec, GloVe)
        • Transformers (e.g., BERT, GPT)
    3. Modeling:

      • Use Machine Learning or Deep Learning models:

        • Traditional: Naive Bayes, SVM
        • Modern: RNNs, LSTMs, Transformers
    4. Output/Inference:

      • The model makes predictions or performs actions based on the text.

    🔍 Real-World Applications of NLP

    • Chatbots & Virtual Assistants (e.g., Siri, Alexa, ChatGPT)
    • Search Engines (e.g., Google)
    • Language Translation (e.g., Google Translate)
    • Spam Filtering
    • Grammar & Writing Tools (e.g., Grammarly)
    • Sentiment Analysis for social media or reviews
    • Voice Assistants in customer service

    📈 Popular NLP Tools & Libraries

    • NLTK (Natural Language Toolkit) – great for academic and beginner-level tasks
    • spaCy – fast and industrial-strength NLP
    • Transformers (by Hugging Face) – state-of-the-art models like BERT, GPT
    • TextBlob – beginner-friendly, easy-to-use
    • OpenAI GPT, BERT, RoBERTa – pre-trained transformer models

    🧪 Example

    Input: "I had a terrible experience with the service."

    Output from a sentiment analysis model: Negative


    Previous topic 15
    Artificial Neural Networks (ANN)
    Next topic 17
    Recent trends and applications of AI algorithms

    Past Papers

    Open this section to load past papers

    Click on Show Past Papers to see past papers.
    On This Page
      Reading Stats
      Est. reading time2 min
      Word count384
      Code examples0
      DifficultyBeginner