| Code |
16684
|
| Year |
3
|
| Semester |
S1
|
| ECTS Credits |
6
|
| Workload |
PL(30H)/T(30H)
|
| Scientific area |
Informatics
|
|
Entry requirements |
Knowing how to program. We will be working with the Python language.
|
|
Learning outcomes |
Natural Language Processing (NLP) seeks to computationally understand and reproduce language, a core aspect of human intelligence. This course combines foundations in linguistics, statistics, logic, and machine learning, covering both classical techniques and recent models such as transformers. Beyond methods, NLP enables everyday applications: search engines, virtual assistants, machine translation, sentiment analysis, and data science support. Mastery of these tools develops technical skills and a critical perspective on the limits, challenges, and responsibilities of systems handling human language. The learning path is practice-oriented: working with real corpora, experimenting with pre-trained models and specialized libraries, and building applicable solutions. By the end, students are expected not only to apply existing tools but also to evaluate and design creative, responsible approaches to new challenges involving text and natural language.
|
|
Syllabus |
1. Introduction, context, and motivation
2. Basic textual operations
3. Lexical modeling
4. Syntactic modeling
5. Document vectorization
6. Lexical vectorization
7. Semantic representation
8. Neural models in NLP
9. Computing with human language
|
|
Main Bibliography |
[1] Daniel Jurafsky and James H. Martin. 2025. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models, 3rd edition. Online manuscript released August 24, 2025. https://web.stanford.edu/~jurafsky/slp3.
[2] Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing with Python (1st. ed.). O'Reilly Media, Inc.
[3] Tunstall, L., Von Werra, L., & Wolf, T. 2022. Natural language processing with transformers. " O'Reilly Media, Inc.".
|
|
Teaching Methodologies and Assessment Criteria |
The assessment process of the course is structured to combine continuous evaluation throughout the semester, encouraging student engagement and practical learning. Continuous assessment includes written exams, a final project, and practical activities, allowing performance to be measured progressively. Final exams integrate a written test and the final project, providing opportunities for recovery. Attendance is also considered, with at least 90% presence required in both theoretical and practical classes. This model aims to ensure that students develop solid technical skills, academic responsibility, and the ability to apply acquired knowledge in real-world situations.
|
|
Language |
Portuguese. Tutorial support is available in English.
|