@inproceedings{dong-choi-2020-xd,
title = "{XD} at {S}em{E}val-2020 Task 12: Ensemble Approach to Offensive Language Identification in Social Media Using Transformer Encoders",
author = "Dong, Xiangjue and
Choi, Jinho D.",
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-1.299/",
doi = "10.18653/v1/2020.semeval-1.299",
pages = "2244--2250",
abstract = "This paper presents six document classification models using the latest transformer encoders and a high-performing ensemble model for a task of offensive language identification in social media. For the individual models, deep transformer layers are applied to perform multi-head attentions. For the ensemble model, the utterance representations taken from those individual models are concatenated and fed into a linear decoder to make the final decisions. Our ensemble model outperforms the individual models and shows up to 8.6{\%} improvement over the individual models on the development set. On the test set, it achieves macro-F1 of 90.9{\%} and becomes one of the high performing systems among 85 participants in the sub-task A of this shared task. Our analysis shows that although the ensemble model significantly improves the accuracy on the development set, the improvement is not as evident on the test set."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-choi-2020-xd">
<titleInfo>
<title>XD at SemEval-2020 Task 12: Ensemble Approach to Offensive Language Identification in Social Media Using Transformer Encoders</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiangjue</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</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 presents six document classification models using the latest transformer encoders and a high-performing ensemble model for a task of offensive language identification in social media. For the individual models, deep transformer layers are applied to perform multi-head attentions. For the ensemble model, the utterance representations taken from those individual models are concatenated and fed into a linear decoder to make the final decisions. Our ensemble model outperforms the individual models and shows up to 8.6% improvement over the individual models on the development set. On the test set, it achieves macro-F1 of 90.9% and becomes one of the high performing systems among 85 participants in the sub-task A of this shared task. Our analysis shows that although the ensemble model significantly improves the accuracy on the development set, the improvement is not as evident on the test set.</abstract>
<identifier type="citekey">dong-choi-2020-xd</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.299</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.299/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2244</start>
<end>2250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T XD at SemEval-2020 Task 12: Ensemble Approach to Offensive Language Identification in Social Media Using Transformer Encoders
%A Dong, Xiangjue
%A Choi, Jinho D.
%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 dong-choi-2020-xd
%X This paper presents six document classification models using the latest transformer encoders and a high-performing ensemble model for a task of offensive language identification in social media. For the individual models, deep transformer layers are applied to perform multi-head attentions. For the ensemble model, the utterance representations taken from those individual models are concatenated and fed into a linear decoder to make the final decisions. Our ensemble model outperforms the individual models and shows up to 8.6% improvement over the individual models on the development set. On the test set, it achieves macro-F1 of 90.9% and becomes one of the high performing systems among 85 participants in the sub-task A of this shared task. Our analysis shows that although the ensemble model significantly improves the accuracy on the development set, the improvement is not as evident on the test set.
%R 10.18653/v1/2020.semeval-1.299
%U https://aclanthology.org/2020.semeval-1.299/
%U https://doi.org/10.18653/v1/2020.semeval-1.299
%P 2244-2250
Markdown (Informal)
[XD at SemEval-2020 Task 12: Ensemble Approach to Offensive Language Identification in Social Media Using Transformer Encoders](https://aclanthology.org/2020.semeval-1.299/) (Dong & Choi, SemEval 2020)
ACL