@inproceedings{modha-etal-2019-da,
title = "{DA}-{LD}-{H}ildesheim at {S}em{E}val-2019 Task 6: Tracking Offensive Content with Deep Learning using Shallow Representation",
author = "Modha, Sandip and
Majumder, Prasenjit and
Patel, Daksh",
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/S19-2103/",
doi = "10.18653/v1/S19-2103",
pages = "577--581",
abstract = "This paper presents the participation of team DA-LD-Hildesheim of Information Retrieval and Language Processing lab at DA-IICT, India in Semeval-19 OffenEval track. The aim of this shared task is to identify offensive content at fined-grained level granularity. The task is divided into three sub-tasks. The system is required to check whether social media posts contain any offensive or profane content or not, targeted or untargeted towards any entity and classifying targeted posts into the individual, group or other categories. Social media posts suffer from data sparsity problem, Therefore, the distributed word representation technique is chosen over the Bag-of-Words for the text representation. Since limited labeled data was available for the training, pre-trained word vectors are used and fine-tuned on this classification task. Various deep learning models based on LSTM, Bidirectional LSTM, CNN, and Stacked CNN are used for the classification. It has been observed that labeled data was highly affected with class imbalance and our technique to handle the class-balance was not effective, in fact performance was degraded in some of the runs. Macro F1 score is used as a primary evaluation metric for the performance. Our System achieves Macro F1 score = 0.7833 in sub-task A, 0.6456 in the sub-task B and 0.5533 in the sub-task C."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="modha-etal-2019-da">
<titleInfo>
<title>DA-LD-Hildesheim at SemEval-2019 Task 6: Tracking Offensive Content with Deep Learning using Shallow Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandip</namePart>
<namePart type="family">Modha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasenjit</namePart>
<namePart type="family">Majumder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daksh</namePart>
<namePart type="family">Patel</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>This paper presents the participation of team DA-LD-Hildesheim of Information Retrieval and Language Processing lab at DA-IICT, India in Semeval-19 OffenEval track. The aim of this shared task is to identify offensive content at fined-grained level granularity. The task is divided into three sub-tasks. The system is required to check whether social media posts contain any offensive or profane content or not, targeted or untargeted towards any entity and classifying targeted posts into the individual, group or other categories. Social media posts suffer from data sparsity problem, Therefore, the distributed word representation technique is chosen over the Bag-of-Words for the text representation. Since limited labeled data was available for the training, pre-trained word vectors are used and fine-tuned on this classification task. Various deep learning models based on LSTM, Bidirectional LSTM, CNN, and Stacked CNN are used for the classification. It has been observed that labeled data was highly affected with class imbalance and our technique to handle the class-balance was not effective, in fact performance was degraded in some of the runs. Macro F1 score is used as a primary evaluation metric for the performance. Our System achieves Macro F1 score = 0.7833 in sub-task A, 0.6456 in the sub-task B and 0.5533 in the sub-task C.</abstract>
<identifier type="citekey">modha-etal-2019-da</identifier>
<identifier type="doi">10.18653/v1/S19-2103</identifier>
<location>
<url>https://aclanthology.org/S19-2103/</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>577</start>
<end>581</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DA-LD-Hildesheim at SemEval-2019 Task 6: Tracking Offensive Content with Deep Learning using Shallow Representation
%A Modha, Sandip
%A Majumder, Prasenjit
%A Patel, Daksh
%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 modha-etal-2019-da
%X This paper presents the participation of team DA-LD-Hildesheim of Information Retrieval and Language Processing lab at DA-IICT, India in Semeval-19 OffenEval track. The aim of this shared task is to identify offensive content at fined-grained level granularity. The task is divided into three sub-tasks. The system is required to check whether social media posts contain any offensive or profane content or not, targeted or untargeted towards any entity and classifying targeted posts into the individual, group or other categories. Social media posts suffer from data sparsity problem, Therefore, the distributed word representation technique is chosen over the Bag-of-Words for the text representation. Since limited labeled data was available for the training, pre-trained word vectors are used and fine-tuned on this classification task. Various deep learning models based on LSTM, Bidirectional LSTM, CNN, and Stacked CNN are used for the classification. It has been observed that labeled data was highly affected with class imbalance and our technique to handle the class-balance was not effective, in fact performance was degraded in some of the runs. Macro F1 score is used as a primary evaluation metric for the performance. Our System achieves Macro F1 score = 0.7833 in sub-task A, 0.6456 in the sub-task B and 0.5533 in the sub-task C.
%R 10.18653/v1/S19-2103
%U https://aclanthology.org/S19-2103/
%U https://doi.org/10.18653/v1/S19-2103
%P 577-581
Markdown (Informal)
[DA-LD-Hildesheim at SemEval-2019 Task 6: Tracking Offensive Content with Deep Learning using Shallow Representation](https://aclanthology.org/S19-2103/) (Modha et al., SemEval 2019)
ACL