AI for Natural Language Processing (NLP) – Introduction
Prepare text data and build introductory NLP models for classification, topic modelling, and text generation.
Get Course Info
Audience: Developers · Data Analysts · Data Scientists
Duration: 3 days
Format: Lectures & hands-on labs (50 % / 50 %)
Overview
Modern NLP techniques let us understand and generate text at scale. This course starts with classic preprocessing (tokenising, TF-IDF, Naïve Bayes) and advances to deep-learning models (RNN, LSTM, Transformers) using libraries such as NLTK, spaCy, TensorFlow, and Hugging Face.
Objective
Prepare text data and build introductory NLP models for classification, topic modelling, and text generation.
What You Will Learn
- Text preprocessing (stemming, tokenising, stop-word removal)
- Bag-of-Words, TF-IDF, word-frequency techniques
- Visualising text data & word clouds
- Naïve Bayes & SVM for text classification
- Word embeddings & Word2Vec
- Topic modelling with Gensim
- Deep-Learning for NLP: RNN, LSTM, Transformers (ELMo, ULMFiT, BERT)
- Text generation with TensorFlow
Course Details
Audience: Developers · Data Analysts · Data Scientists
Duration: 3 days
Format: Lectures & hands-on labs (50 % / 50 %)
- Programming background
- Basic Python & Jupyter notebooks
Setup: Cloud-based lab (Google Colab recommended) · Laptop · Chrome
Detailed Outline
- AI vocabulary
- ML types
- Hardware / software ecosystem
- Filtering & stop-words
- Stemming & tokenisation
- Word clouds
- Unicode handling
- Lab
- N-grams
- Bag-of-Words
- Vectorising text
- Lab
- Naïve Bayes
- SVM
- Lab
- LDA
- Gensim
- Lab
- Word embeddings
- RNN & LSTM
- Transformers & attention
- Lab: text generation
- Intro to Rasa framework
- Group exercise on real dataset
Ready to Get Started?
Contact us to learn more about this course and schedule your training.