@inproceedings{hua-2019-understanding,
title = "Understanding {BERT} performance in propaganda analysis",
author = "Hua, Yiqing",
editor = "Feldman, Anna and
Da San Martino, Giovanni and
Barr{\'o}n-Cede{\~n}o, Alberto and
Brew, Chris and
Leberknight, Chris and
Nakov, Preslav",
booktitle = "Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5019",
doi = "10.18653/v1/D19-5019",
pages = "135--138",
abstract = "In this paper, we describe our system used in the shared task for fine-grained propaganda analysis at sentence level. Despite the challenging nature of the task, our pretrained BERT model (team YMJA) fine tuned on the training dataset provided by the shared task scored 0.62 F1 on the test set and ranked third among 25 teams who participated in the contest. We present a set of illustrative experiments to better understand the performance of our BERT model on this shared task. Further, we explore beyond the given dataset for false-positive cases that likely to be produced by our system. We show that despite the high performance on the given testset, our system may have the tendency of classifying opinion pieces as propaganda and cannot distinguish quotations of propaganda speech from actual usage of propaganda techniques.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hua-2019-understanding">
<titleInfo>
<title>Understanding BERT performance in propaganda analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiqing</namePart>
<namePart type="family">Hua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Barrón-Cedeño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Brew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Leberknight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe our system used in the shared task for fine-grained propaganda analysis at sentence level. Despite the challenging nature of the task, our pretrained BERT model (team YMJA) fine tuned on the training dataset provided by the shared task scored 0.62 F1 on the test set and ranked third among 25 teams who participated in the contest. We present a set of illustrative experiments to better understand the performance of our BERT model on this shared task. Further, we explore beyond the given dataset for false-positive cases that likely to be produced by our system. We show that despite the high performance on the given testset, our system may have the tendency of classifying opinion pieces as propaganda and cannot distinguish quotations of propaganda speech from actual usage of propaganda techniques.</abstract>
<identifier type="citekey">hua-2019-understanding</identifier>
<identifier type="doi">10.18653/v1/D19-5019</identifier>
<location>
<url>https://aclanthology.org/D19-5019</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>135</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Understanding BERT performance in propaganda analysis
%A Hua, Yiqing
%Y Feldman, Anna
%Y Da San Martino, Giovanni
%Y Barrón-Cedeño, Alberto
%Y Brew, Chris
%Y Leberknight, Chris
%Y Nakov, Preslav
%S Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F hua-2019-understanding
%X In this paper, we describe our system used in the shared task for fine-grained propaganda analysis at sentence level. Despite the challenging nature of the task, our pretrained BERT model (team YMJA) fine tuned on the training dataset provided by the shared task scored 0.62 F1 on the test set and ranked third among 25 teams who participated in the contest. We present a set of illustrative experiments to better understand the performance of our BERT model on this shared task. Further, we explore beyond the given dataset for false-positive cases that likely to be produced by our system. We show that despite the high performance on the given testset, our system may have the tendency of classifying opinion pieces as propaganda and cannot distinguish quotations of propaganda speech from actual usage of propaganda techniques.
%R 10.18653/v1/D19-5019
%U https://aclanthology.org/D19-5019
%U https://doi.org/10.18653/v1/D19-5019
%P 135-138
Markdown (Informal)
[Understanding BERT performance in propaganda analysis](https://aclanthology.org/D19-5019) (Hua, NLP4IF 2019)
ACL
- Yiqing Hua. 2019. Understanding BERT performance in propaganda analysis. In Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda, pages 135–138, Hong Kong, China. Association for Computational Linguistics.