Participants will learn about text-based data sources, retrieval solutions, and data preprocessing techniques, including tokenization and text representation methods. The course delves into sentiment analysis, text classification, part-of-speech tagging, and named entity recognition, with practical exercises in building domain-specific systems. Participants will explore sequence labeling, sequence-to-sequence models, and neural language models for text generation. The course concludes with an overview of question answering, dialog systems, and a review of existing solutions in NLP, along with discussions on new research results and future trends in the field.
- ECTS credits: 6 ECTS
- Places available: 10
- Format: On-site
- Language: Lithuanian
- Target: ICT graduates
- Price: Free of charge
- Contact: simona.ramanauskaite@vilniustech.lt
- More information here.