Section outline

• Select section Day 1 – Introduction & Preprocessing

  Day 1 – Introduction & Preprocessing

  Collapse all Expand all

  • Text indexing and IR fundamentals

  • Regex, BeautifulSoup for HTML extraction

  • Textract for PDFs and Word documents

  • SpaCy setup and Jupyter usage

  • Numpy and Pandas for data handling
• Select section Day 2 – Core NLP & Classification

  Day 2 – Core NLP & Classification

  • Tokenization, Stemming, Lemmatization

  • POS Tagging and Named Entity Recognition

  • Bag of Words, TF-IDF, and N-gram models

  • Logistic Regression for Text Classification

  • Project: IMDB Comment Classifier
• Select section Day 3 – Sentiment Analysis & Word Embeddings

  Day 3 – Sentiment Analysis & Word Embeddings

  • Twitter API integration and tweet processing

  • Sentiment prediction using trained TF-IDF models

  • Text summarization using scoring models

  • Word2Vec and pretrained models (GloVe)

  • Text generation basics using neural nets
• Select section Day 4 – Conversational AI with RASA

  Day 4 – Conversational AI with RASA

  • Creating a RASA assistant

  • Entities, intents, stories, forms, rules

  • Model evaluation and confidence interpretation

  • Introduction to Rasa X and Conversational-Driven Development (CDD)