Building a corpus of the Croatian parliamentary debates using UDPipe open source NLP tools and Neo4j graph database for creation of social ontology model, text classification and extraction of semantic information (CROSBI ID 667018)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Perak, Benedikt ; Rodik, Filip
engleski
Building a corpus of the Croatian parliamentary debates using UDPipe open source NLP tools and Neo4j graph database for creation of social ontology model, text classification and extraction of semantic information
This paper describes a process of creating morphosyntactically tagged corpus of the Croatian parliamentary debates using NLP tool UDapi for tokenization, morpho-syntactic parsing and processing Universal Dependencies data to process over 300 thousand transcribed parliamentary speech utterances produced over the period from 2003- 2017 and store the data in a Neo4j graph database.
corpus linguistics, graph database, universal dependencies, parliamentary debates
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
2016-220.
2018.
nije evidentirano
objavljeno
978-961-06-0111-1
Podaci o matičnoj publikaciji
Proceedings of the Conference on Language Technologies & Digital Humanities 2018
Fišer, D. ; Pančur, A.
Ljubljana: Fakulteta za elektrotehniko, Univerza v Ljubljani
Podaci o skupu
Jezikovne tehnologije in digitalna humanistika 2018
poster
20.09.2018-21.09.2018
Ljubljana, Slovenija