Automatic Genre Classification of Czech Texts Based on Syntactic Functions
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3ANUZA74QN" target="_blank" >RIV/00216208:11320/26:NUZA74QN - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-031-55917-4_13" target="_blank" >http://dx.doi.org/10.1007/978-3-031-55917-4_13</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-55917-4_13" target="_blank" >10.1007/978-3-031-55917-4_13</a>
Alternative languages
Result language
angličtina
Original language name
Automatic Genre Classification of Czech Texts Based on Syntactic Functions
Original language description
Although there has been research conducted on text classification based on syntactic features for decades, the recent development of accurate automatic syntactic taggers has enabled scholars to apply the methods to much larger and more diverse datasets than before. This study aims to classify various text types in Czech language using relative frequencies of syntactic functions (as they are defined in the Prague Dependency Treebank (PDT)). A large balanced corpus of contemporary written Czech SYN2020 is used as the language material. The distances between texts are calculated by the Cosine Delta method and then hierarchical cluster analysis is performed. The results indicate that syntactic functions can contribute to automatic genre classification based on large empirical language data. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Stud. Classif., Data Anal., Knowl. Organ.
ISBN
978-3-031-55916-7
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
163-172
Publisher name
Springer Science and Business Media Deutschland GmbH
Place of publication
—
Event location
Naples, Italy
Event date
Jan 1, 2026
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—