@inproceedings{rogoz-etal-2021-saroco,
title = "{S}a{R}o{C}o: Detecting Satire in a Novel {R}omanian Corpus of News Articles",
author = "Rogoz, Ana-Cristina and
Mihaela, Gaman and
Ionescu, Radu Tudor",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.136",
doi = "10.18653/v1/2021.acl-short.136",
pages = "1073--1079",
abstract = "In this work, we introduce a corpus for satire detection in Romanian news. We gathered 55,608 public news articles from multiple real and satirical news sources, composing one of the largest corpora for satire detection regardless of language and the only one for the Romanian language. We provide an official split of the text samples, such that training news articles belong to different sources than test news articles, thus ensuring that models do not achieve high performance simply due to overfitting. We conduct experiments with two state-of-the-art deep neural models, resulting in a set of strong baselines for our novel corpus. Our results show that the machine-level accuracy for satire detection in Romanian is quite low (under 73{\%} on the test set) compared to the human-level accuracy (87{\%}), leaving enough room for improvement in future research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rogoz-etal-2021-saroco">
<titleInfo>
<title>SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ana-Cristina</namePart>
<namePart type="family">Rogoz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaman</namePart>
<namePart type="family">Mihaela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="given">Tudor</namePart>
<namePart type="family">Ionescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we introduce a corpus for satire detection in Romanian news. We gathered 55,608 public news articles from multiple real and satirical news sources, composing one of the largest corpora for satire detection regardless of language and the only one for the Romanian language. We provide an official split of the text samples, such that training news articles belong to different sources than test news articles, thus ensuring that models do not achieve high performance simply due to overfitting. We conduct experiments with two state-of-the-art deep neural models, resulting in a set of strong baselines for our novel corpus. Our results show that the machine-level accuracy for satire detection in Romanian is quite low (under 73% on the test set) compared to the human-level accuracy (87%), leaving enough room for improvement in future research.</abstract>
<identifier type="citekey">rogoz-etal-2021-saroco</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.136</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.136</url>
</location>
<part>
<date>2021-aug</date>
<extent unit="page">
<start>1073</start>
<end>1079</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles
%A Rogoz, Ana-Cristina
%A Mihaela, Gaman
%A Ionescu, Radu Tudor
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 aug
%I Association for Computational Linguistics
%C Online
%F rogoz-etal-2021-saroco
%X In this work, we introduce a corpus for satire detection in Romanian news. We gathered 55,608 public news articles from multiple real and satirical news sources, composing one of the largest corpora for satire detection regardless of language and the only one for the Romanian language. We provide an official split of the text samples, such that training news articles belong to different sources than test news articles, thus ensuring that models do not achieve high performance simply due to overfitting. We conduct experiments with two state-of-the-art deep neural models, resulting in a set of strong baselines for our novel corpus. Our results show that the machine-level accuracy for satire detection in Romanian is quite low (under 73% on the test set) compared to the human-level accuracy (87%), leaving enough room for improvement in future research.
%R 10.18653/v1/2021.acl-short.136
%U https://aclanthology.org/2021.acl-short.136
%U https://doi.org/10.18653/v1/2021.acl-short.136
%P 1073-1079
Markdown (Informal)
[SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles](https://aclanthology.org/2021.acl-short.136) (Rogoz et al., ACL 2021)
ACL
- Ana-Cristina Rogoz, Gaman Mihaela, and Radu Tudor Ionescu. 2021. SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 1073–1079, Online. Association for Computational Linguistics.