After attending this session, participants will be able to:

• Understand the main concepts and applications of Natural Language Processing.
• Apply common text preprocessing and representation techniques.
• Understand the differences between classical NLP approaches and Transformer-based models.
• Build and evaluate text classification workflows.
• Use pre-trained models for Named Entity Recognition.
• Understand the differences between extractive and abstractive text summarization.
• Apply pre-trained models for summarizing text and documents.
• Understand the main concepts behind Large Language Models and Transformer architectures.
• Use LLMs for text classification, entity recognition and summarization.
• Understand the main limitations and risks associated with LLM-based applications, including hallucinations, cost and data privacy.

Natural Language Processing is widely used in applications such as search engines, chatbots, document processing, analytics and automated content analysis. Modern NLP combines classical text processing techniques with Transformer-based models and Large Language Models.

This course provides a practical introduction to key NLP tasks, including text classification, Named Entity Recognition and text summarization. Participants will explore both traditional and modern approaches, from Bag of Words and TF-IDF to embeddings and Transformer-based models.

The training also introduces Large Language Models and shows how they can be used for common NLP tasks without requiring model fine-tuning. Practical demonstrations will cover text classification, entity extraction, summarization and prompt-based approaches.

The course is focused on practical examples and real-world use cases, while also addressing important limitations such as hallucinations, computational costs and data privacy.

Participants should have:

• Basic knowledge of Python
• Introductory knowledge of Machine Learning