@inproceedings{doxolodeo-mahendra-2020-ui,
title = "{UI} at {S}em{E}val-2020 Task 4: Commonsense Validation and Explanation by Exploiting Contradiction",
author = "Doxolodeo, Kerenza and
Mahendra, Rahmad",
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-1.78",
doi = "10.18653/v1/2020.semeval-1.78",
pages = "614--619",
abstract = "This paper describes our submissions into the ComVe challenge, the SemEval 2020 Task 4. This evaluation task consists of three sub-tasks that test commonsense comprehension by identifying sentences that do not make sense and explain why they do not. In subtask A, we use Roberta to find which sentence does not make sense. In subtask B, besides using BERT, we also experiment with replacing the dataset with MNLI when selecting the best explanation from the provided options why the given sentence does not make sense. In subtask C, we utilize the MNLI model from subtask B to evaluate the explanation generated by Roberta and GPT-2 by exploiting the contradiction of the sentence and their explanation. Our system submission records a performance of 88.2{\%}, 80.5{\%}, and BLEU 5.5 for those three subtasks, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doxolodeo-mahendra-2020-ui">
<titleInfo>
<title>UI at SemEval-2020 Task 4: Commonsense Validation and Explanation by Exploiting Contradiction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kerenza</namePart>
<namePart type="family">Doxolodeo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahmad</namePart>
<namePart type="family">Mahendra</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 describes our submissions into the ComVe challenge, the SemEval 2020 Task 4. This evaluation task consists of three sub-tasks that test commonsense comprehension by identifying sentences that do not make sense and explain why they do not. In subtask A, we use Roberta to find which sentence does not make sense. In subtask B, besides using BERT, we also experiment with replacing the dataset with MNLI when selecting the best explanation from the provided options why the given sentence does not make sense. In subtask C, we utilize the MNLI model from subtask B to evaluate the explanation generated by Roberta and GPT-2 by exploiting the contradiction of the sentence and their explanation. Our system submission records a performance of 88.2%, 80.5%, and BLEU 5.5 for those three subtasks, respectively.</abstract>
<identifier type="citekey">doxolodeo-mahendra-2020-ui</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.78</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.78</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>614</start>
<end>619</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UI at SemEval-2020 Task 4: Commonsense Validation and Explanation by Exploiting Contradiction
%A Doxolodeo, Kerenza
%A Mahendra, Rahmad
%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 doxolodeo-mahendra-2020-ui
%X This paper describes our submissions into the ComVe challenge, the SemEval 2020 Task 4. This evaluation task consists of three sub-tasks that test commonsense comprehension by identifying sentences that do not make sense and explain why they do not. In subtask A, we use Roberta to find which sentence does not make sense. In subtask B, besides using BERT, we also experiment with replacing the dataset with MNLI when selecting the best explanation from the provided options why the given sentence does not make sense. In subtask C, we utilize the MNLI model from subtask B to evaluate the explanation generated by Roberta and GPT-2 by exploiting the contradiction of the sentence and their explanation. Our system submission records a performance of 88.2%, 80.5%, and BLEU 5.5 for those three subtasks, respectively.
%R 10.18653/v1/2020.semeval-1.78
%U https://aclanthology.org/2020.semeval-1.78
%U https://doi.org/10.18653/v1/2020.semeval-1.78
%P 614-619
Markdown (Informal)
[UI at SemEval-2020 Task 4: Commonsense Validation and Explanation by Exploiting Contradiction](https://aclanthology.org/2020.semeval-1.78) (Doxolodeo & Mahendra, SemEval 2020)
ACL