Course detail

Natural Language Processing

FIT-ZPJaAcad. year: 2017/2018

Foundations of the natural language processing, language data in corpora, levels of description: phonetics and phonology, morphology, syntax, semantics and pragmatics. Traditional vs. formal grammars: representation of morphological and syntactic structures, meaning representation. context-free grammars and their context-sensitive extensions, DCG (Definite Clause Grammars), CKY algorithm (Cocke-Kasami-Younger), chart-parsing. Problem of ambiguity. Electronic dictionaries: representation of lexical knowledge. Types of the machine readable dictionaries. Semantic representation of sentence meaning. The Compositionality Principle, composition of meaning. Semantic classification: valency frames, predicates, ontologies, transparent intensional logic (TIL) and its application to semantic analysis of sentences. Pragmatics: semantic and pragmatic nature of noun groups, discourse structure, deictic expressions, verbal and non-verbal contexts. Natural language understanding: semantic representation, inference and knowledge representations.

Language of instruction

English

Number of ECTS credits

Mode of study

Not applicable.

Guarantor

doc. RNDr. Pavel Smrž, Ph.D.

Department

Department of Computer Graphics and Multimedia (UPGM)

Offered to foreign students

Of all faculties

Learning outcomes of the course unit

The students will get acquainted with natural language processing and learn how to apply basic algorithms in this field. They will understand the algorithmic description of the main language levels: morphology, syntax, semantics, and pragmatics, as well as the resources of natural language data - corpora. They will also grasp basics of knowledge representation, inference, and relations to the artificial intelligence.

The students will learn to work in a team. They will also improve their programming skills and their knowledge of development tools.

Prerequisites

Basic knowledge of C/C++ programming or a scripting language (Perl, Python, Ruby)

Co-requisites

Not applicable.

Planned learning activities and teaching methods

Not applicable.

Assesment methods and criteria linked to learning outcomes

Study evaluation is based on marks obtained for specified items. Minimimum number of marks to pass is 50.

Realized individual project

Course curriculum

Syllabus of lectures:

Introduction, history of NLP, subdisciplines
How to build a Google-like search engine, text categorization, document similarity
Morphological analysis, inflective and derivational morphology, trie structure for dictionaries
Syntactical analysis, constituent and dependency structures, feature structures, grammar specification formats
Grammar formalisms, categorial grammars, LFG, HPSG, LTAG
Methods of syntactic analysis, CKY-algorithm, chart-parsing
Korpus linguistics, treebanks, TBL method
Probabilistic context-free analysis, automatic alignment, machine translation
Lexical semantics, dictionaries vs. encyclopedias, compositionality
Transparent intensional logic for the description of meaning
Pragmatics, contextual meaning relations, dynamic semantics
Knowledge representation, possible-world semantics, inference
The Semantic Web technologies, ontologies, OWL

Syllabus - others, projects and individual work of students:

Individually assigned projects

Work placements

Not applicable.

Aims

To understand natural language processing and to learn how to apply basic algorithms in this field. To get acquainted with the algorithmic description of the main language levels: morphology, syntax, semantics, and pragmatics, as well as the resources of natural language data - corpora. To conceive basics of knowledge representation, inference, and relations to the artificial intelligence.

Specification of controlled education, way of implementation and compensation for absences

The evaluation includes mid-term test, individual project, and the final exam. The mid-term test does not have a correction option, the final exam has two possible correction terms

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Not applicable.

VUT

Faculties

University Institutes

Parts

Natural Language Processing