@inproceedings{ghosh-etal-2020-iitp,
title = "{IITP}-{AINLPML} at {S}em{E}val-2020 Task 12: Offensive Tweet Identification and Target Categorization in a Multitask Environment",
author = "Ghosh, Soumitra and
Ekbal, Asif and
Bhattacharyya, Pushpak",
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-1.261/",
doi = "10.18653/v1/2020.semeval-1.261",
pages = "1983--1991",
abstract = "In this paper, we describe the participation of IITP-AINLPML team in the SemEval-2020 SharedTask 12 on Offensive Language Identification and Target Categorization in English Twitter data. Our proposed model learns to extract textual features using a BiGRU-based deep neural network supported by a Hierarchical Attention architecture to focus on the most relevant areas in the text. We leverage the effectiveness of multitask learning while building our models for sub-task A and B. We do necessary undersampling of the over-represented classes in the sub-tasks A and C.During training, we consider a threshold of 0.5 as the separation margin between the instances belonging to classes OFF and NOT in sub-task A and UNT and TIN in sub-task B. For sub-task C, the class corresponding to the maximum score among the given confidence scores of the classes(IND, GRP and OTH) is considered as the final label for an instance. Our proposed model obtains the macro F1-scores of 90.95{\%}, 55.69{\%} and 63.88{\%} in sub-task A, B and C, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghosh-etal-2020-iitp">
<titleInfo>
<title>IITP-AINLPML at SemEval-2020 Task 12: Offensive Tweet Identification and Target Categorization in a Multitask Environment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soumitra</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</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 participation of IITP-AINLPML team in the SemEval-2020 SharedTask 12 on Offensive Language Identification and Target Categorization in English Twitter data. Our proposed model learns to extract textual features using a BiGRU-based deep neural network supported by a Hierarchical Attention architecture to focus on the most relevant areas in the text. We leverage the effectiveness of multitask learning while building our models for sub-task A and B. We do necessary undersampling of the over-represented classes in the sub-tasks A and C.During training, we consider a threshold of 0.5 as the separation margin between the instances belonging to classes OFF and NOT in sub-task A and UNT and TIN in sub-task B. For sub-task C, the class corresponding to the maximum score among the given confidence scores of the classes(IND, GRP and OTH) is considered as the final label for an instance. Our proposed model obtains the macro F1-scores of 90.95%, 55.69% and 63.88% in sub-task A, B and C, respectively.</abstract>
<identifier type="citekey">ghosh-etal-2020-iitp</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.261</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.261/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1983</start>
<end>1991</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IITP-AINLPML at SemEval-2020 Task 12: Offensive Tweet Identification and Target Categorization in a Multitask Environment
%A Ghosh, Soumitra
%A Ekbal, Asif
%A Bhattacharyya, Pushpak
%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 ghosh-etal-2020-iitp
%X In this paper, we describe the participation of IITP-AINLPML team in the SemEval-2020 SharedTask 12 on Offensive Language Identification and Target Categorization in English Twitter data. Our proposed model learns to extract textual features using a BiGRU-based deep neural network supported by a Hierarchical Attention architecture to focus on the most relevant areas in the text. We leverage the effectiveness of multitask learning while building our models for sub-task A and B. We do necessary undersampling of the over-represented classes in the sub-tasks A and C.During training, we consider a threshold of 0.5 as the separation margin between the instances belonging to classes OFF and NOT in sub-task A and UNT and TIN in sub-task B. For sub-task C, the class corresponding to the maximum score among the given confidence scores of the classes(IND, GRP and OTH) is considered as the final label for an instance. Our proposed model obtains the macro F1-scores of 90.95%, 55.69% and 63.88% in sub-task A, B and C, respectively.
%R 10.18653/v1/2020.semeval-1.261
%U https://aclanthology.org/2020.semeval-1.261/
%U https://doi.org/10.18653/v1/2020.semeval-1.261
%P 1983-1991
Markdown (Informal)
[IITP-AINLPML at SemEval-2020 Task 12: Offensive Tweet Identification and Target Categorization in a Multitask Environment](https://aclanthology.org/2020.semeval-1.261/) (Ghosh et al., SemEval 2020)
ACL