@inproceedings{jurkiewicz-etal-2020-applicaai,
title = "{A}pplica{AI} at {S}em{E}val-2020 Task 11: On {R}o{BERT}a-{CRF}, Span {CLS} and Whether Self-Training Helps Them",
author = "Jurkiewicz, Dawid and
Borchmann, {\L}ukasz and
Kosmala, Izabela and
Grali{\'n}ski, Filip",
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-1.187/",
doi = "10.18653/v1/2020.semeval-1.187",
pages = "1415--1424",
abstract = "This paper presents the winning system for the propaganda Technique Classification (TC) task and the second-placed system for the propaganda Span Identification (SI) task. The purpose of TC task was to identify an applied propaganda technique given propaganda text fragment. The goal of SI task was to find specific text fragments which contain at least one propaganda technique. Both of the developed solutions used semi-supervised learning technique of self-training. Interestingly, although CRF is barely used with transformer-based language models, the SI task was approached with RoBERTa-CRF architecture. An ensemble of RoBERTa-based models was proposed for the TC task, with one of them making use of Span CLS layers we introduce in the present paper. In addition to describing the submitted systems, an impact of architectural decisions and training schemes is investigated along with remarks regarding training models of the same or better quality with lower computational budget. Finally, the results of error analysis are presented."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jurkiewicz-etal-2020-applicaai">
<titleInfo>
<title>ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dawid</namePart>
<namePart type="family">Jurkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Łukasz</namePart>
<namePart type="family">Borchmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Izabela</namePart>
<namePart type="family">Kosmala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Graliński</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 the winning system for the propaganda Technique Classification (TC) task and the second-placed system for the propaganda Span Identification (SI) task. The purpose of TC task was to identify an applied propaganda technique given propaganda text fragment. The goal of SI task was to find specific text fragments which contain at least one propaganda technique. Both of the developed solutions used semi-supervised learning technique of self-training. Interestingly, although CRF is barely used with transformer-based language models, the SI task was approached with RoBERTa-CRF architecture. An ensemble of RoBERTa-based models was proposed for the TC task, with one of them making use of Span CLS layers we introduce in the present paper. In addition to describing the submitted systems, an impact of architectural decisions and training schemes is investigated along with remarks regarding training models of the same or better quality with lower computational budget. Finally, the results of error analysis are presented.</abstract>
<identifier type="citekey">jurkiewicz-etal-2020-applicaai</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.187</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.187/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1415</start>
<end>1424</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them
%A Jurkiewicz, Dawid
%A Borchmann, Łukasz
%A Kosmala, Izabela
%A Graliński, Filip
%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 jurkiewicz-etal-2020-applicaai
%X This paper presents the winning system for the propaganda Technique Classification (TC) task and the second-placed system for the propaganda Span Identification (SI) task. The purpose of TC task was to identify an applied propaganda technique given propaganda text fragment. The goal of SI task was to find specific text fragments which contain at least one propaganda technique. Both of the developed solutions used semi-supervised learning technique of self-training. Interestingly, although CRF is barely used with transformer-based language models, the SI task was approached with RoBERTa-CRF architecture. An ensemble of RoBERTa-based models was proposed for the TC task, with one of them making use of Span CLS layers we introduce in the present paper. In addition to describing the submitted systems, an impact of architectural decisions and training schemes is investigated along with remarks regarding training models of the same or better quality with lower computational budget. Finally, the results of error analysis are presented.
%R 10.18653/v1/2020.semeval-1.187
%U https://aclanthology.org/2020.semeval-1.187/
%U https://doi.org/10.18653/v1/2020.semeval-1.187
%P 1415-1424
Markdown (Informal)
[ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them](https://aclanthology.org/2020.semeval-1.187/) (Jurkiewicz et al., SemEval 2020)
ACL