Description

Theory
2

Laboratory
2

Instructors

Luiz Faria

Contents

1.Introductory Concepts of Natural Language Processing
Sintax and Semantic
Text Comprehension
Text Generation
Automatic Translation
Knowledge-based Natural Language Processing
2.Text Classification
Text Preprocessing
Feature Extraction from Text
Linear Models for Sentiment Analysis
Deep Learning for Text Classification
3.Language Modeling and Sequence Tagging
Probabilistic Language Modeling
Sequence Tagging with Probabilistic Models
Sequential Models for Named Entity Recognition
Sequence Tagging with Deep Learning (RNN-LSTM)
4.Vector Space Models of Semantics
Word and Sentence Embeddings
Topic Modelling
Topic Models Applied for Search and Data Exploration
5.Sequence to Sequence Tasks
Machine Translation, Summarization, Question Answering
Statistical Machine Translation
Encoder-decoder Architecture with Attention Mechanism
Training seq2seq Neural Networks
6.Conversational Systems
7.LLM
Transformer Architecture
Fine-tuning
RAG and Knowledge Graphs

Learning Outcomes

CO1- Identify the types of problems that can be solved through the application of automatic natural language processing techniques (NB3)
CO2- Identify and apply the appropriate techniques for solving different problems in the area of automatic natural language processing (NB6)
CO3- Develop transversal skills related to teamwork in response to challenges (AI Challenges4Teams) (NB6)