Automatic Genre Classification of Czech Texts Based on Syntactic Functions

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17250%2F24%3AA25038JG" target="_blank" >RIV/61988987:17250/24:A25038JG - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-55917-4_13" target="_blank" >https://link.springer.com/chapter/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>

Jazyk výsledku

angličtina

Název v původním jazyce

Automatic Genre Classification of Czech Texts Based on Syntactic Functions

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Automatic Genre Classification of Czech Texts Based on Syntactic Functions

Popis výsledku anglicky

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.

Druh

C - Kapitola v odborné knize

CEP obor

—

OECD FORD obor

60203 - Linguistics

Projekt

<a href="/cs/project/GA22-20632S" target="_blank" >GA22-20632S: Kvantitativní syntaktická stylistika současné psané češtiny</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název knihy nebo sborníku

New Frontiers in Textual Data Analysis

ISBN

978-3-031-55916-7

Počet stran výsledku

10

Strana od-do

163-172

Počet stran knihy

396

Název nakladatele

Springer

Místo vydání

Cham

Kód UT WoS kapitoly

—