@inproceedings{swamy-etal-2019-nit,
title = "{NIT}{\_}{A}gartala{\_}{NLP}{\_}{T}eam at {S}em{E}val-2019 Task 6: An Ensemble Approach to Identifying and Categorizing Offensive Language in {T}witter Social Media Corpora",
author = {Swamy, Steve Durairaj and
Jamatia, Anupam and
Gamb{\"a}ck, Bj{\"o}rn and
Das, Amitava},
editor = "May, Jonathan and
Shutova, Ekaterina and
Herbelot, Aurelie and
Zhu, Xiaodan and
Apidianaki, Marianna and
Mohammad, Saif M.",
booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S19-2124",
doi = "10.18653/v1/S19-2124",
pages = "696--703",
abstract = "The paper describes the systems submitted to OffensEval (SemEval 2019, Task 6) on {`}Identifying and Categorizing Offensive Language in Social Media{'} by the {`}NIT{\_}Agartala{\_}NLP{\_}Team{'}. A Twitter annotated dataset of 13,240 English tweets was provided by the task organizers to train the individual models, with the best results obtained using an ensemble model composed of six different classifiers. The ensemble model produced macro-averaged F1-scores of 0.7434, 0.7078 and 0.4853 on Subtasks A, B, and C, respectively. The paper highlights the overall low predictive nature of various linguistic features and surface level count features, as well as the limitations of a traditional machine learning approach when compared to a Deep Learning counterpart.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="swamy-etal-2019-nit">
<titleInfo>
<title>NIT_Agartala_NLP_Team at SemEval-2019 Task 6: An Ensemble Approach to Identifying and Categorizing Offensive Language in Twitter Social Media Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="given">Durairaj</namePart>
<namePart type="family">Swamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anupam</namePart>
<namePart type="family">Jamatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Björn</namePart>
<namePart type="family">Gambäck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amitava</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Workshop on Semantic Evaluation</title>
</titleInfo>
<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>
<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">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper describes the systems submitted to OffensEval (SemEval 2019, Task 6) on ‘Identifying and Categorizing Offensive Language in Social Media’ by the ‘NIT_Agartala_NLP_Team’. A Twitter annotated dataset of 13,240 English tweets was provided by the task organizers to train the individual models, with the best results obtained using an ensemble model composed of six different classifiers. The ensemble model produced macro-averaged F1-scores of 0.7434, 0.7078 and 0.4853 on Subtasks A, B, and C, respectively. The paper highlights the overall low predictive nature of various linguistic features and surface level count features, as well as the limitations of a traditional machine learning approach when compared to a Deep Learning counterpart.</abstract>
<identifier type="citekey">swamy-etal-2019-nit</identifier>
<identifier type="doi">10.18653/v1/S19-2124</identifier>
<location>
<url>https://aclanthology.org/S19-2124</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>696</start>
<end>703</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NIT_Agartala_NLP_Team at SemEval-2019 Task 6: An Ensemble Approach to Identifying and Categorizing Offensive Language in Twitter Social Media Corpora
%A Swamy, Steve Durairaj
%A Jamatia, Anupam
%A Gambäck, Björn
%A Das, Amitava
%Y May, Jonathan
%Y Shutova, Ekaterina
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Apidianaki, Marianna
%Y Mohammad, Saif M.
%S Proceedings of the 13th International Workshop on Semantic Evaluation
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota, USA
%F swamy-etal-2019-nit
%X The paper describes the systems submitted to OffensEval (SemEval 2019, Task 6) on ‘Identifying and Categorizing Offensive Language in Social Media’ by the ‘NIT_Agartala_NLP_Team’. A Twitter annotated dataset of 13,240 English tweets was provided by the task organizers to train the individual models, with the best results obtained using an ensemble model composed of six different classifiers. The ensemble model produced macro-averaged F1-scores of 0.7434, 0.7078 and 0.4853 on Subtasks A, B, and C, respectively. The paper highlights the overall low predictive nature of various linguistic features and surface level count features, as well as the limitations of a traditional machine learning approach when compared to a Deep Learning counterpart.
%R 10.18653/v1/S19-2124
%U https://aclanthology.org/S19-2124
%U https://doi.org/10.18653/v1/S19-2124
%P 696-703
Markdown (Informal)
[NIT_Agartala_NLP_Team at SemEval-2019 Task 6: An Ensemble Approach to Identifying and Categorizing Offensive Language in Twitter Social Media Corpora](https://aclanthology.org/S19-2124) (Swamy et al., SemEval 2019)
ACL