@inproceedings{mikhalkova-etal-2020-utmn,
title = "{UTMN} at {S}em{E}val-2020 Task 11: A Kitchen Solution to Automatic Propaganda Detection",
author = "Mikhalkova, Elena and
Ganzherli, Nadezhda and
Glazkova, Anna and
Bidulya, Yuliya",
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-1.245",
doi = "10.18653/v1/2020.semeval-1.245",
pages = "1858--1864",
abstract = "The article describes a fast solution to propaganda detection at SemEval-2020 Task 11, based on feature adjustment. We use per-token vectorization of features and a simple Logistic Regression classifier to quickly test different hypotheses about our data. We come up with what seems to us the best solution, however, we are unable to align it with the result of the metric suggested by the organizers of the task. We test how our system handles class and feature imbalance by varying the number of samples of two classes (Propaganda and None) in the training set, the size of a context window in which a token is vectorized and combination of vectorization means. The result of our system at SemEval2020 Task 11 is F-score=0.37.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mikhalkova-etal-2020-utmn">
<titleInfo>
<title>UTMN at SemEval-2020 Task 11: A Kitchen Solution to Automatic Propaganda Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Mikhalkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadezhda</namePart>
<namePart type="family">Ganzherli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Glazkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuliya</namePart>
<namePart type="family">Bidulya</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>The article describes a fast solution to propaganda detection at SemEval-2020 Task 11, based on feature adjustment. We use per-token vectorization of features and a simple Logistic Regression classifier to quickly test different hypotheses about our data. We come up with what seems to us the best solution, however, we are unable to align it with the result of the metric suggested by the organizers of the task. We test how our system handles class and feature imbalance by varying the number of samples of two classes (Propaganda and None) in the training set, the size of a context window in which a token is vectorized and combination of vectorization means. The result of our system at SemEval2020 Task 11 is F-score=0.37.</abstract>
<identifier type="citekey">mikhalkova-etal-2020-utmn</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.245</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.245</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1858</start>
<end>1864</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UTMN at SemEval-2020 Task 11: A Kitchen Solution to Automatic Propaganda Detection
%A Mikhalkova, Elena
%A Ganzherli, Nadezhda
%A Glazkova, Anna
%A Bidulya, Yuliya
%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 mikhalkova-etal-2020-utmn
%X The article describes a fast solution to propaganda detection at SemEval-2020 Task 11, based on feature adjustment. We use per-token vectorization of features and a simple Logistic Regression classifier to quickly test different hypotheses about our data. We come up with what seems to us the best solution, however, we are unable to align it with the result of the metric suggested by the organizers of the task. We test how our system handles class and feature imbalance by varying the number of samples of two classes (Propaganda and None) in the training set, the size of a context window in which a token is vectorized and combination of vectorization means. The result of our system at SemEval2020 Task 11 is F-score=0.37.
%R 10.18653/v1/2020.semeval-1.245
%U https://aclanthology.org/2020.semeval-1.245
%U https://doi.org/10.18653/v1/2020.semeval-1.245
%P 1858-1864
Markdown (Informal)
[UTMN at SemEval-2020 Task 11: A Kitchen Solution to Automatic Propaganda Detection](https://aclanthology.org/2020.semeval-1.245) (Mikhalkova et al., SemEval 2020)
ACL