Introduction to Text Processing and Analysis - AMLV00067

• Anglický název: Introduction to Text Processing and Analysis
• Zajišťuje: Ústav českého národního korpusu (21-UCNK)
• Fakulta: Filozofická fakulta
• Platnost: od 2019
• Semestr: zimní
• Body: 0
• E-Kredity: 4
• Způsob provedení zkoušky: zimní s.:
• Rozsah, examinace: zimní s.:1/1, Z [HT]
• Počet míst: neurčen / neurčen (neurčen)
• Minimální obsazenost: neomezen
• 4EU+: ne
• Virtuální mobilita / počet míst pro virtuální mobilitu: ne
• Stav předmětu: nevyučován
• Jazyk výuky: angličtina
• Způsob výuky: prezenční
• Poznámka: předmět je možno zapsat mimo plán; povolen pro zápis po webu
• Garant: Mgr. Pavel Vondřička, Ph.D.; Mgr. Lucie Lukešová, Ph.D.

Anotace

The main objective of the course is to provide beginner-level digital linguistics students with all the necessary
information on text processing and analysis. Starting with basic topics, such as characteristics of a plain text format
and the difference between data and metadata, the course goes on to explain the specifics of XML and different
types of text annotation, to introduce the process of tokenization, segmentation and morphological analysis, to
describe the limits and possibilities of syntactic and semantic tagging and, finally, to summarize the principles of
CQL and corpus querying, including the use of regular expressions and querying parallel corpora.

Poslední úprava: Lukešová Lucie, Mgr., Ph.D. (12.07.2018)

Cíl předmětu

1. To understand how computers work with textual data;

2. To distinguish between different data formats and extract textual content from them (e.g. using OCR);

3. To understand the specifics of plain text and XML formats;

4. To understand the principles and issues of text annotation, incl. morphological analysis, syntactic and semantic tagging;

5. To learn about available resources for text processing and analysis, including taggers and concordancers;

6. To be able to analyse existing as well as own corpora in a variety of available corpus-based tools;

7. To build complex CQL queries, including regular expressions and logical operators.

Poslední úprava: Lukešová Lucie, Mgr., Ph.D. (12.07.2018)

Sylabus

1. File formats related to textual data

2. Plain text: Encoding, data and metadata

3. Extensible Markup Language or XML

4. Regular expressions

5. Tokenization and corpus-data formats

6. Morphological analysis: principles and tools

7. Syntactic and semantic annotation

8. Corpus exploration and analysis

9. Querying corpus data with CQL

10. Text alignment and parallel corpora

Poslední úprava: Lukešová Lucie, Mgr., Ph.D. (12.07.2018)