@inproceedings{liu-etal-2021-uor,
title = "{U}o{R} at {S}em{E}val-2021 Task 7: Utilizing Pre-trained {D}istil{BERT} Model and Multi-scale {CNN} for Humor Detection",
author = "Liu, Zehao and
Haines, Carl and
Liang, Huizhi",
editor = "Palmer, Alexis and
Schneider, Nathan and
Schluter, Natalie and
Emerson, Guy and
Herbelot, Aurelie and
Zhu, Xiaodan",
booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.semeval-1.166/",
doi = "10.18653/v1/2021.semeval-1.166",
pages = "1179--1184",
abstract = "Humour detection is an interesting but difficult task in NLP. Because humorous might not be obvious in text, it can be embedded into context, hide behind the literal meaning and require prior knowledge to understand. We explored different shallow and deep methods to create a humour detection classifier for task 7-1a. Models like Logistic Regression, LSTM, MLP, CNN were used, and pre-trained models like DistilBert were introduced to generate accurate vector representation for textual data. We focused on applying multi-scale strategy on modelling, and compared different models. Our best model is the DistilBERT+MultiScale CNN, it used different sizes of CNN kernel to get multiple scales of features, which achieved 93.7{\%} F1-score and 92.1{\%} accuracy on the test set."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-uor">
<titleInfo>
<title>UoR at SemEval-2021 Task 7: Utilizing Pre-trained DistilBERT Model and Multi-scale CNN for Humor Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zehao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="family">Haines</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huizhi</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)</title>
</titleInfo>
<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">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Humour detection is an interesting but difficult task in NLP. Because humorous might not be obvious in text, it can be embedded into context, hide behind the literal meaning and require prior knowledge to understand. We explored different shallow and deep methods to create a humour detection classifier for task 7-1a. Models like Logistic Regression, LSTM, MLP, CNN were used, and pre-trained models like DistilBert were introduced to generate accurate vector representation for textual data. We focused on applying multi-scale strategy on modelling, and compared different models. Our best model is the DistilBERT+MultiScale CNN, it used different sizes of CNN kernel to get multiple scales of features, which achieved 93.7% F1-score and 92.1% accuracy on the test set.</abstract>
<identifier type="citekey">liu-etal-2021-uor</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.166</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.166/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1179</start>
<end>1184</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UoR at SemEval-2021 Task 7: Utilizing Pre-trained DistilBERT Model and Multi-scale CNN for Humor Detection
%A Liu, Zehao
%A Haines, Carl
%A Liang, Huizhi
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Schluter, Natalie
%Y Emerson, Guy
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F liu-etal-2021-uor
%X Humour detection is an interesting but difficult task in NLP. Because humorous might not be obvious in text, it can be embedded into context, hide behind the literal meaning and require prior knowledge to understand. We explored different shallow and deep methods to create a humour detection classifier for task 7-1a. Models like Logistic Regression, LSTM, MLP, CNN were used, and pre-trained models like DistilBert were introduced to generate accurate vector representation for textual data. We focused on applying multi-scale strategy on modelling, and compared different models. Our best model is the DistilBERT+MultiScale CNN, it used different sizes of CNN kernel to get multiple scales of features, which achieved 93.7% F1-score and 92.1% accuracy on the test set.
%R 10.18653/v1/2021.semeval-1.166
%U https://aclanthology.org/2021.semeval-1.166/
%U https://doi.org/10.18653/v1/2021.semeval-1.166
%P 1179-1184
Markdown (Informal)
[UoR at SemEval-2021 Task 7: Utilizing Pre-trained DistilBERT Model and Multi-scale CNN for Humor Detection](https://aclanthology.org/2021.semeval-1.166/) (Liu et al., SemEval 2021)
ACL