@inproceedings{fadel-etal-2020-justers,
title = "{JUST}ers at {S}em{E}val-2020 Task 4: Evaluating Transformer Models against Commonsense Validation and Explanation",
author = "Fadel, Ali and
Al-Ayyoub, Mahmoud and
Cambria, Erik",
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-1.66",
doi = "10.18653/v1/2020.semeval-1.66",
pages = "535--542",
abstract = "In this paper, we describe our team{'}s (JUSTers) effort in the Commonsense Validation and Explanation (ComVE) task, which is part of SemEval2020. We evaluate five pre-trained Transformer-based language models with various sizes against the three proposed subtasks. For the first two subtasks, the best accuracy levels achieved by our models are 92.90{\%} and 92.30{\%}, respectively, placing our team in the 12th and 9th places, respectively. As for the last subtask, our models reach 16.10 BLEU score and 1.94 human evaluation score placing our team in the 5th and 3rd places according to these two metrics, respectively. The latter is only 0.16 away from the 1st place human evaluation score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fadel-etal-2020-justers">
<titleInfo>
<title>JUSTers at SemEval-2020 Task 4: Evaluating Transformer Models against Commonsense Validation and Explanation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Fadel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Al-Ayyoub</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Cambria</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>In this paper, we describe our team’s (JUSTers) effort in the Commonsense Validation and Explanation (ComVE) task, which is part of SemEval2020. We evaluate five pre-trained Transformer-based language models with various sizes against the three proposed subtasks. For the first two subtasks, the best accuracy levels achieved by our models are 92.90% and 92.30%, respectively, placing our team in the 12th and 9th places, respectively. As for the last subtask, our models reach 16.10 BLEU score and 1.94 human evaluation score placing our team in the 5th and 3rd places according to these two metrics, respectively. The latter is only 0.16 away from the 1st place human evaluation score.</abstract>
<identifier type="citekey">fadel-etal-2020-justers</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.66</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.66</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>535</start>
<end>542</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JUSTers at SemEval-2020 Task 4: Evaluating Transformer Models against Commonsense Validation and Explanation
%A Fadel, Ali
%A Al-Ayyoub, Mahmoud
%A Cambria, Erik
%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 fadel-etal-2020-justers
%X In this paper, we describe our team’s (JUSTers) effort in the Commonsense Validation and Explanation (ComVE) task, which is part of SemEval2020. We evaluate five pre-trained Transformer-based language models with various sizes against the three proposed subtasks. For the first two subtasks, the best accuracy levels achieved by our models are 92.90% and 92.30%, respectively, placing our team in the 12th and 9th places, respectively. As for the last subtask, our models reach 16.10 BLEU score and 1.94 human evaluation score placing our team in the 5th and 3rd places according to these two metrics, respectively. The latter is only 0.16 away from the 1st place human evaluation score.
%R 10.18653/v1/2020.semeval-1.66
%U https://aclanthology.org/2020.semeval-1.66
%U https://doi.org/10.18653/v1/2020.semeval-1.66
%P 535-542
Markdown (Informal)
[JUSTers at SemEval-2020 Task 4: Evaluating Transformer Models against Commonsense Validation and Explanation](https://aclanthology.org/2020.semeval-1.66) (Fadel et al., SemEval 2020)
ACL