Ficha

Versión en español

Course: 2019/2020

Natural Language Processing

(18504)

Study: Bachelor in Sound and Image Engineering (214)

Coordinating teacher: MARTÍNEZ OLMOS, PABLO

Department assigned to the subject: Department of Signal and Communications Theory

Type: Electives

ECTS Credits: 3.0 ECTS

Course:

Semester:

Students are expected to have completed

The students are expected to have basic knowledge of - Calculus - Programming skills - Statistics

Competences and skills that will be acquired and learning results. Further information on this link

- Know the basic techniques of text pre-processing. - Use software tools for pre-processing text. - Know the techniques of topic modeling. - Use topic modeling software tools in corpus of documents. - Use topic models for information retrieval in corpus of documents. - Learn how to train models of semantic representation in a vector space. - Learn to train language models using recursive neural networks. - Know basic translation structures based on recursive neural networks. - Use optimization tools to build language models with recursive neural networks.

Description of contents: programme

- Document preprocessing techniques - Topic Modeling - Recurrent Neural Networks - Language Models with RNNs - Sequence to Sequence for Machine Translation - Attention Models

Learning activities and methodology

Lectures (1.5 ECTS): Contents: basic theory and methods of natural language processing systems. Methodology: classical lecture with use of slides, videos and white/blackboard. Lab projects (1.5 ECTS): Contents: implementation of algorithms in for the simulation and assessment of natural language processing systems. Methodology: use of numerical software packages (matlab/octave) to study the performance of algorithms and systems.

Assessment System

The continuous evaluation (80%) is based on programming projects to implement the tools seen in class and a presentation of recent articles in the field.

There will be a final exam that will count 20%.

% end-of-term-examination 20
% of continuous assessment (assigments, laboratory, practicals...) 80

Basic Bibliography

Cristopher Bishop. Pattern Recognition and Machine Learning. Springer. 2006
Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning. MIT Press. 2017
Steven Bird, Ewan Klein, Edward Loper . Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. O'Reilly. 2009

The course syllabus and the academic weekly planning may change due academic events or other reasons.