Introduction

SouDeC (Source Detection and Classification) is an on-line tool and REST API service for detecting and classifying citation sources in Czech texts. Taking a plain text (typically, a newspaper article) as an input, it runs external services for dependency parsing and named entities recognition and then identifies citation phrases and sources in the text and classifies each source into one of five classes: anonymous, anonymous-partial, unofficial, official-non-political, official-political.

The software is available under the Creative Commons CC BY-NC-SA licence.

Copyright 2023 by Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University, Czech Republic.

Description of the available methods is available in the API Documentation.

Online Web Application and Web Service

SouDeC Web Application is available at http://quest.ms.mff.cuni.cz/soudec/.

SouDeC REST Web Service is also available, with the API documentation available at http://quest.ms.mff.cuni.cz/soudec/api-reference.php.

SouDeC User's Manual

SouDeC User's Manual is available on a separate page.

SouDeC API Reference

SouDeC API Reference is available on a separate page.

Contact

Authors:

• Jiří Mírovský, mirovsky@ufal.mff.cuni.cz
• Barbora Hladká, hladka@ufal.mff.cuni.cz

Acknowledgements

The development of SouDeC was financed by the TAČR project TL05000057: Signál a šum v éře Žurnalistiky 5.0 - komparativní perspektiva novinářských žánrů automatizovaných obsahů.

SouDeC uses external services for its work:

• UDPipe (https://lindat.mff.cuni.cz/services/udpipe/)
• NameTag (http://lindat.mff.cuni.cz/services/nametag/)

This work has been using language resources developed, stored or distributed by the LINDAT/CLARIAH-CZ project of the Ministry of Education of the Czech Republic (project LM2023062).