Descripción y contextualización de la asignatura

El estudiante realiza un primer curso completo en la misma.

Resultados del aprendizaje de la asignatura

* Tener conocimiento y manejo de algoritmos de aprendizaje automático

* Tener criterios para diseñar experimentos para procesamiento del lenguaje

* Tener conocimiento sobre estadística inferencial con el foco en los métodos usados habitualmente en el área de la lingüística experimental

* Tener conocimientos de las técnicas principales de traducción automática en PLN, especialmente de las técnicas basadas en aprendizaje profundo.

Temario

* Foundational : Statistical methods; symbolic methods; cognition; corpus; text and speech; foundations of linguistics.

* Computational Syntax and Morphology : Finite state techniques; probabilistic approaches; formal grammars; tagging, chunking; parsing.

* Computational Semantics, Pragmatics and Discourse: Syntax-semantics interface; semantic construction; dialogue; ontologies; formal semantics.

* Data Structures, Data Organization and Processing : Algebraic data-types; relational databases; semi-structured data and XML; information retrieval; digital libraries.

* Logic, Computability and Complexity: Logic and inference; automata theory; computability theory; complexity theory; discrete mathematics.

* Formal Languages and Algorithms: Formal grammars and languages hierarchy; parsing and compiler design; search techniques and constraint resolution; automated learning.

* Advanced Language Technologies: Machine translation; information and knowledge representation; information retrieval; question answering; speech recognition and generation; models of human language processing and understanding; psycholinguistics.

*Advanced Computer Science: Artificial intelligence; knowledge representation; automated reasoning; semantic web; intelligent and multi-modal interfaces; cognitive modelling; computational psychology; neural networks; machine learning.