@inproceedings{collins-etal-2020-mxgra,
title = "Mxgra at {S}em{E}val-2020 Task 4: Common Sense Making with Next Token Prediction",
author = "Collins, Kris and
Grathwohl, Max and
Ahmed, Heba",
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-1.71",
doi = "10.18653/v1/2020.semeval-1.71",
pages = "569--573",
abstract = "In this paper, we explore solutions to a common sense making task in which a model must discern which of two sentences is against common sense. We used a pre-trained language model which we used to calculate complexity scores for input to discern which sentence contained an unlikely sequence of tokens. Other approaches we tested were word vector distances, which were used to find semantic outliers within a sentence, and siamese network. By using the pre-trained language model to calculate perplexity scores based on the sequence of tokens in input sentences, we achieved an accuracy of 75 percent.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="collins-etal-2020-mxgra">
<titleInfo>
<title>Mxgra at SemEval-2020 Task 4: Common Sense Making with Next Token Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kris</namePart>
<namePart type="family">Collins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Grathwohl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heba</namePart>
<namePart type="family">Ahmed</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 explore solutions to a common sense making task in which a model must discern which of two sentences is against common sense. We used a pre-trained language model which we used to calculate complexity scores for input to discern which sentence contained an unlikely sequence of tokens. Other approaches we tested were word vector distances, which were used to find semantic outliers within a sentence, and siamese network. By using the pre-trained language model to calculate perplexity scores based on the sequence of tokens in input sentences, we achieved an accuracy of 75 percent.</abstract>
<identifier type="citekey">collins-etal-2020-mxgra</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.71</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.71</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>569</start>
<end>573</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mxgra at SemEval-2020 Task 4: Common Sense Making with Next Token Prediction
%A Collins, Kris
%A Grathwohl, Max
%A Ahmed, Heba
%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 collins-etal-2020-mxgra
%X In this paper, we explore solutions to a common sense making task in which a model must discern which of two sentences is against common sense. We used a pre-trained language model which we used to calculate complexity scores for input to discern which sentence contained an unlikely sequence of tokens. Other approaches we tested were word vector distances, which were used to find semantic outliers within a sentence, and siamese network. By using the pre-trained language model to calculate perplexity scores based on the sequence of tokens in input sentences, we achieved an accuracy of 75 percent.
%R 10.18653/v1/2020.semeval-1.71
%U https://aclanthology.org/2020.semeval-1.71
%U https://doi.org/10.18653/v1/2020.semeval-1.71
%P 569-573
Markdown (Informal)
[Mxgra at SemEval-2020 Task 4: Common Sense Making with Next Token Prediction](https://aclanthology.org/2020.semeval-1.71) (Collins et al., SemEval 2020)
ACL