@inproceedings{janiszewski-etal-2020-pum,
title = "{PUM} at {S}em{E}val-2020 Task 12: Aggregation of Transformer-based Models{'} Features for Offensive Language Recognition",
author = "Janiszewski, Piotr and
Skiba, Mateusz and
Wali{\'n}ska, Urszula",
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-1.210",
doi = "10.18653/v1/2020.semeval-1.210",
pages = "1615--1621",
abstract = "In this paper, we describe the PUM team{'}s entry to the SemEval-2020 Task 12. Creating our solution involved leveraging two well-known pretrained models used in natural language processing: BERT and XLNet, which achieve state-of-the-art results in multiple NLP tasks. The models were fine-tuned for each subtask separately and features taken from their hidden layers were combinedand fed into a fully connected neural network. The model using aggregated Transformer featurescan serve as a powerful tool for offensive language identification problem. Our team was ranked7th out of 40 in Sub-task C - Offense target identification with 64.727{\%} macro F1-score and 64thout of 85 in Sub-task A - Offensive language identification (89.726{\%} F1-score).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="janiszewski-etal-2020-pum">
<titleInfo>
<title>PUM at SemEval-2020 Task 12: Aggregation of Transformer-based Models’ Features for Offensive Language Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Janiszewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Skiba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Urszula</namePart>
<namePart type="family">Walińska</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 describe the PUM team’s entry to the SemEval-2020 Task 12. Creating our solution involved leveraging two well-known pretrained models used in natural language processing: BERT and XLNet, which achieve state-of-the-art results in multiple NLP tasks. The models were fine-tuned for each subtask separately and features taken from their hidden layers were combinedand fed into a fully connected neural network. The model using aggregated Transformer featurescan serve as a powerful tool for offensive language identification problem. Our team was ranked7th out of 40 in Sub-task C - Offense target identification with 64.727% macro F1-score and 64thout of 85 in Sub-task A - Offensive language identification (89.726% F1-score).</abstract>
<identifier type="citekey">janiszewski-etal-2020-pum</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.210</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.210</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1615</start>
<end>1621</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PUM at SemEval-2020 Task 12: Aggregation of Transformer-based Models’ Features for Offensive Language Recognition
%A Janiszewski, Piotr
%A Skiba, Mateusz
%A Walińska, Urszula
%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 janiszewski-etal-2020-pum
%X In this paper, we describe the PUM team’s entry to the SemEval-2020 Task 12. Creating our solution involved leveraging two well-known pretrained models used in natural language processing: BERT and XLNet, which achieve state-of-the-art results in multiple NLP tasks. The models were fine-tuned for each subtask separately and features taken from their hidden layers were combinedand fed into a fully connected neural network. The model using aggregated Transformer featurescan serve as a powerful tool for offensive language identification problem. Our team was ranked7th out of 40 in Sub-task C - Offense target identification with 64.727% macro F1-score and 64thout of 85 in Sub-task A - Offensive language identification (89.726% F1-score).
%R 10.18653/v1/2020.semeval-1.210
%U https://aclanthology.org/2020.semeval-1.210
%U https://doi.org/10.18653/v1/2020.semeval-1.210
%P 1615-1621
Markdown (Informal)
[PUM at SemEval-2020 Task 12: Aggregation of Transformer-based Models’ Features for Offensive Language Recognition](https://aclanthology.org/2020.semeval-1.210) (Janiszewski et al., SemEval 2020)
ACL