@inproceedings{chen-dhingra-2023-hierarchical,
title = "Hierarchical Multi-Instance Multi-Label Learning for Detecting Propaganda Techniques",
author = "Chen, Anni and
Dhingra, Bhuwan",
editor = "Can, Burcu and
Mozes, Maximilian and
Cahyawijaya, Samuel and
Saphra, Naomi and
Kassner, Nora and
Ravfogel, Shauli and
Ravichander, Abhilasha and
Zhao, Chen and
Augenstein, Isabelle and
Rogers, Anna and
Cho, Kyunghyun and
Grefenstette, Edward and
Voita, Lena",
booktitle = "Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.repl4nlp-1.13",
doi = "10.18653/v1/2023.repl4nlp-1.13",
pages = "155--163",
abstract = "Since the introduction of the SemEval 2020 Task 11 (CITATION), several approaches have been proposed in the literature for classifying propagandabased on the rhetorical techniques used to influence readers. These methods, however, classify one span at a time, ignoring dependencies from the labels of other spans within the same context. In this paper, we approach propaganda technique classification as aMulti-Instance Multi-Label (MIML) learning problem (CITATION) and propose a simple RoBERTa-based model (CITATION) for classifying all spans in an article simultaneously. Further, we note that, due to the annotation process whereannotators classified the spans by following a decision tree,there is an inherent hierarchical relationship among the differenttechniques, which existing approaches ignore. We incorporate these hierarchical label dependencies by adding an auxiliary classifier for each node in the decision tree to the training objective and ensembling the predictions from the original and auxiliary classifiers at test time. Overall, our model leads to an absolute improvement of 2.47{\%} micro-F1 over the model from the shared task winning team in a cross-validation setup and is the best performing non-ensemble model on the shared task leaderboard.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-dhingra-2023-hierarchical">
<titleInfo>
<title>Hierarchical Multi-Instance Multi-Label Learning for Detecting Propaganda Techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anni</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhuwan</namePart>
<namePart type="family">Dhingra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Mozes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Kassner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shauli</namePart>
<namePart type="family">Ravfogel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhilasha</namePart>
<namePart type="family">Ravichander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Grefenstette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Voita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Since the introduction of the SemEval 2020 Task 11 (CITATION), several approaches have been proposed in the literature for classifying propagandabased on the rhetorical techniques used to influence readers. These methods, however, classify one span at a time, ignoring dependencies from the labels of other spans within the same context. In this paper, we approach propaganda technique classification as aMulti-Instance Multi-Label (MIML) learning problem (CITATION) and propose a simple RoBERTa-based model (CITATION) for classifying all spans in an article simultaneously. Further, we note that, due to the annotation process whereannotators classified the spans by following a decision tree,there is an inherent hierarchical relationship among the differenttechniques, which existing approaches ignore. We incorporate these hierarchical label dependencies by adding an auxiliary classifier for each node in the decision tree to the training objective and ensembling the predictions from the original and auxiliary classifiers at test time. Overall, our model leads to an absolute improvement of 2.47% micro-F1 over the model from the shared task winning team in a cross-validation setup and is the best performing non-ensemble model on the shared task leaderboard.</abstract>
<identifier type="citekey">chen-dhingra-2023-hierarchical</identifier>
<identifier type="doi">10.18653/v1/2023.repl4nlp-1.13</identifier>
<location>
<url>https://aclanthology.org/2023.repl4nlp-1.13</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>155</start>
<end>163</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hierarchical Multi-Instance Multi-Label Learning for Detecting Propaganda Techniques
%A Chen, Anni
%A Dhingra, Bhuwan
%Y Can, Burcu
%Y Mozes, Maximilian
%Y Cahyawijaya, Samuel
%Y Saphra, Naomi
%Y Kassner, Nora
%Y Ravfogel, Shauli
%Y Ravichander, Abhilasha
%Y Zhao, Chen
%Y Augenstein, Isabelle
%Y Rogers, Anna
%Y Cho, Kyunghyun
%Y Grefenstette, Edward
%Y Voita, Lena
%S Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chen-dhingra-2023-hierarchical
%X Since the introduction of the SemEval 2020 Task 11 (CITATION), several approaches have been proposed in the literature for classifying propagandabased on the rhetorical techniques used to influence readers. These methods, however, classify one span at a time, ignoring dependencies from the labels of other spans within the same context. In this paper, we approach propaganda technique classification as aMulti-Instance Multi-Label (MIML) learning problem (CITATION) and propose a simple RoBERTa-based model (CITATION) for classifying all spans in an article simultaneously. Further, we note that, due to the annotation process whereannotators classified the spans by following a decision tree,there is an inherent hierarchical relationship among the differenttechniques, which existing approaches ignore. We incorporate these hierarchical label dependencies by adding an auxiliary classifier for each node in the decision tree to the training objective and ensembling the predictions from the original and auxiliary classifiers at test time. Overall, our model leads to an absolute improvement of 2.47% micro-F1 over the model from the shared task winning team in a cross-validation setup and is the best performing non-ensemble model on the shared task leaderboard.
%R 10.18653/v1/2023.repl4nlp-1.13
%U https://aclanthology.org/2023.repl4nlp-1.13
%U https://doi.org/10.18653/v1/2023.repl4nlp-1.13
%P 155-163
Markdown (Informal)
[Hierarchical Multi-Instance Multi-Label Learning for Detecting Propaganda Techniques](https://aclanthology.org/2023.repl4nlp-1.13) (Chen & Dhingra, RepL4NLP 2023)
ACL