@inproceedings{dementieva-etal-2020-skoltechnlp,
title = "{S}koltech{NLP} at {S}em{E}val-2020 Task 11: Exploring Unsupervised Text Augmentation for Propaganda Detection",
author = "Dementieva, Daryna and
Markov, Igor and
Panchenko, Alexander",
editor = "Herbelot, Aurelie and
Zhu, Xiaodan and
Palmer, Alexis and
Schneider, Nathan and
May, Jonathan and
Shutova, Ekaterina",
booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
month = dec,
year = "2020",
address = "Barcelona (online)",
publisher = "International Committee for Computational Linguistics",
url = "https://aclanthology.org/2020.semeval-1.234/",
doi = "10.18653/v1/2020.semeval-1.234",
pages = "1786--1792",
abstract = "This paper presents a solution for the Span Identification (SI) task in the {\textquotedblleft}Detection of Propaganda Techniques in News Articles{\textquotedblright} competition at SemEval-2020. The goal of the SI task is to identify specific fragments of each article which contain the use of at least one propaganda technique. This is a binary sequence tagging task. We tested several approaches finally selecting a fine-tuned BERT model as our baseline model. Our main contribution is an investigation of several unsupervised data augmentation techniques based on distributional semantics expanding the original small training dataset as applied to this BERT-based sequence tagger. We explore various expansion strategies and show that they can substantially shift the balance between precision and recall, while maintaining comparable levels of the F1 score."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dementieva-etal-2020-skoltechnlp">
<titleInfo>
<title>SkoltechNLP at SemEval-2020 Task 11: Exploring Unsupervised Text Augmentation for Propaganda Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Markov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a solution for the Span Identification (SI) task in the “Detection of Propaganda Techniques in News Articles” competition at SemEval-2020. The goal of the SI task is to identify specific fragments of each article which contain the use of at least one propaganda technique. This is a binary sequence tagging task. We tested several approaches finally selecting a fine-tuned BERT model as our baseline model. Our main contribution is an investigation of several unsupervised data augmentation techniques based on distributional semantics expanding the original small training dataset as applied to this BERT-based sequence tagger. We explore various expansion strategies and show that they can substantially shift the balance between precision and recall, while maintaining comparable levels of the F1 score.</abstract>
<identifier type="citekey">dementieva-etal-2020-skoltechnlp</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.234</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.234/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1786</start>
<end>1792</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SkoltechNLP at SemEval-2020 Task 11: Exploring Unsupervised Text Augmentation for Propaganda Detection
%A Dementieva, Daryna
%A Markov, Igor
%A Panchenko, Alexander
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y May, Jonathan
%Y Shutova, Ekaterina
%S Proceedings of the Fourteenth Workshop on Semantic Evaluation
%D 2020
%8 December
%I International Committee for Computational Linguistics
%C Barcelona (online)
%F dementieva-etal-2020-skoltechnlp
%X This paper presents a solution for the Span Identification (SI) task in the “Detection of Propaganda Techniques in News Articles” competition at SemEval-2020. The goal of the SI task is to identify specific fragments of each article which contain the use of at least one propaganda technique. This is a binary sequence tagging task. We tested several approaches finally selecting a fine-tuned BERT model as our baseline model. Our main contribution is an investigation of several unsupervised data augmentation techniques based on distributional semantics expanding the original small training dataset as applied to this BERT-based sequence tagger. We explore various expansion strategies and show that they can substantially shift the balance between precision and recall, while maintaining comparable levels of the F1 score.
%R 10.18653/v1/2020.semeval-1.234
%U https://aclanthology.org/2020.semeval-1.234/
%U https://doi.org/10.18653/v1/2020.semeval-1.234
%P 1786-1792
Markdown (Informal)
[SkoltechNLP at SemEval-2020 Task 11: Exploring Unsupervised Text Augmentation for Propaganda Detection](https://aclanthology.org/2020.semeval-1.234/) (Dementieva et al., SemEval 2020)
ACL