Aim of the course
The aim of the course is to present the problems of natural language processing. There are presented the basic problems and ways to solve them. The fields of usage are presented as well.
Natural Languages: Natural language and formal language. Units of natural language - word, sentence, text. Word: Morphology - inflection dictionary, lexical semantics - the conceptual vocabulary (thesaurus). Sentence: Syntax - syntactic structure of sentences (parsing). Semantics: semantic structure of sentences (sentence comprehension). Text: The theory of context. Knowledge representation. Inference. Reading comprehension. Generating dictionary text - indices and concordance. Generating a profile text - automatic text classification. Generating the abstracts of text. Automatic search / filtering text information. Automatic translation of text. Processing of spoken text - text-to-speech and speech-to-text.
Overview of the course elements
The course also includes laboratory classes. The content of the classes consolidates and extends the knowledge taught during the lectures. Students learn the basic tools and algorithms used for natural language processing.
1. D.Jurafsky, J.H. Martin, “ SPEECH and LANGUAGE PROCESSING - An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition”, Prentice Hall, 2008
2. Ch.D.Manning, H.Schutze, “Foundations of Statistical Natural Language Processing”, MIT Press, Cambridge Massachusetts, MIT Press Cambridge Mass, 1999
3. W. Lubaszewski, “Słowniki komputerowe i automatyczna ekstrakcja informacji z tekstu”, UWND AGH, 2009