@inproceedings{morishita-etal-2020-hitachi-semeval,
title = "Hitachi at {S}em{E}val-2020 Task 7: Stacking at Scale with Heterogeneous Language Models for Humor Recognition",
author = "Morishita, Terufumi and
Morio, Gaku and
Ozaki, Hiroaki and
Miyoshi, Toshinori",
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-1.101",
doi = "10.18653/v1/2020.semeval-1.101",
pages = "791--803",
abstract = "This paper describes the winning system for SemEval-2020 task 7: Assessing Humor in Edited News Headlines. Our strategy is Stacking at Scale (SaS) with heterogeneous pre-trained language models (PLMs) such as BERT and GPT-2. SaS first performs fine-tuning on numbers of PLMs with various hyperparameters and then applies a powerful stacking ensemble on top of the fine-tuned PLMs. Our experimental results show that SaS outperforms a naive average ensemble, leveraging weaker PLMs as well as high-performing PLMs. Interestingly, the results show that SaS captured non-funny semantics. Consequently, the system was ranked 1st in all subtasks by significant margins compared with other systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morishita-etal-2020-hitachi-semeval">
<titleInfo>
<title>Hitachi at SemEval-2020 Task 7: Stacking at Scale with Heterogeneous Language Models for Humor Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Terufumi</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Ozaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshinori</namePart>
<namePart type="family">Miyoshi</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 the winning system for SemEval-2020 task 7: Assessing Humor in Edited News Headlines. Our strategy is Stacking at Scale (SaS) with heterogeneous pre-trained language models (PLMs) such as BERT and GPT-2. SaS first performs fine-tuning on numbers of PLMs with various hyperparameters and then applies a powerful stacking ensemble on top of the fine-tuned PLMs. Our experimental results show that SaS outperforms a naive average ensemble, leveraging weaker PLMs as well as high-performing PLMs. Interestingly, the results show that SaS captured non-funny semantics. Consequently, the system was ranked 1st in all subtasks by significant margins compared with other systems.</abstract>
<identifier type="citekey">morishita-etal-2020-hitachi-semeval</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.101</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.101</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>791</start>
<end>803</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hitachi at SemEval-2020 Task 7: Stacking at Scale with Heterogeneous Language Models for Humor Recognition
%A Morishita, Terufumi
%A Morio, Gaku
%A Ozaki, Hiroaki
%A Miyoshi, Toshinori
%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 morishita-etal-2020-hitachi-semeval
%X This paper describes the winning system for SemEval-2020 task 7: Assessing Humor in Edited News Headlines. Our strategy is Stacking at Scale (SaS) with heterogeneous pre-trained language models (PLMs) such as BERT and GPT-2. SaS first performs fine-tuning on numbers of PLMs with various hyperparameters and then applies a powerful stacking ensemble on top of the fine-tuned PLMs. Our experimental results show that SaS outperforms a naive average ensemble, leveraging weaker PLMs as well as high-performing PLMs. Interestingly, the results show that SaS captured non-funny semantics. Consequently, the system was ranked 1st in all subtasks by significant margins compared with other systems.
%R 10.18653/v1/2020.semeval-1.101
%U https://aclanthology.org/2020.semeval-1.101
%U https://doi.org/10.18653/v1/2020.semeval-1.101
%P 791-803
Markdown (Informal)
[Hitachi at SemEval-2020 Task 7: Stacking at Scale with Heterogeneous Language Models for Humor Recognition](https://aclanthology.org/2020.semeval-1.101) (Morishita et al., SemEval 2020)
ACL