@inproceedings{pelicon-etal-2019-embeddia,
title = "Embeddia at {S}em{E}val-2019 Task 6: Detecting Hate with Neural Network and Transfer Learning Approaches",
author = "Pelicon, Andra{\v{z}} and
Martinc, Matej and
Kralj Novak, Petra",
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/S19-2108",
doi = "10.18653/v1/S19-2108",
pages = "604--610",
abstract = "SemEval 2019 Task 6 was OffensEval: Identifying and Categorizing Offensive Language in Social Media. The task was further divided into three sub-tasks: offensive language identification, automatic categorization of offense types, and offense target identification. In this paper, we present the approaches used by the Embeddia team, who qualified as fourth, eighteenth and fifth on the tree sub-tasks. A different model was trained for each sub-task. For the first sub-task, we used a BERT model fine-tuned on the OLID dataset, while for the second and third tasks we developed a custom neural network architecture which combines bag-of-words features and automatically generated sequence-based features. Our results show that combining automatically and manually crafted features fed into a neural architecture outperform transfer learning approach on more unbalanced datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pelicon-etal-2019-embeddia">
<titleInfo>
<title>Embeddia at SemEval-2019 Task 6: Detecting Hate with Neural Network and Transfer Learning Approaches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andraž</namePart>
<namePart type="family">Pelicon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matej</namePart>
<namePart type="family">Martinc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petra</namePart>
<namePart type="family">Kralj Novak</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>SemEval 2019 Task 6 was OffensEval: Identifying and Categorizing Offensive Language in Social Media. The task was further divided into three sub-tasks: offensive language identification, automatic categorization of offense types, and offense target identification. In this paper, we present the approaches used by the Embeddia team, who qualified as fourth, eighteenth and fifth on the tree sub-tasks. A different model was trained for each sub-task. For the first sub-task, we used a BERT model fine-tuned on the OLID dataset, while for the second and third tasks we developed a custom neural network architecture which combines bag-of-words features and automatically generated sequence-based features. Our results show that combining automatically and manually crafted features fed into a neural architecture outperform transfer learning approach on more unbalanced datasets.</abstract>
<identifier type="citekey">pelicon-etal-2019-embeddia</identifier>
<identifier type="doi">10.18653/v1/S19-2108</identifier>
<location>
<url>https://aclanthology.org/S19-2108</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>604</start>
<end>610</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Embeddia at SemEval-2019 Task 6: Detecting Hate with Neural Network and Transfer Learning Approaches
%A Pelicon, Andraž
%A Martinc, Matej
%A Kralj Novak, Petra
%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 pelicon-etal-2019-embeddia
%X SemEval 2019 Task 6 was OffensEval: Identifying and Categorizing Offensive Language in Social Media. The task was further divided into three sub-tasks: offensive language identification, automatic categorization of offense types, and offense target identification. In this paper, we present the approaches used by the Embeddia team, who qualified as fourth, eighteenth and fifth on the tree sub-tasks. A different model was trained for each sub-task. For the first sub-task, we used a BERT model fine-tuned on the OLID dataset, while for the second and third tasks we developed a custom neural network architecture which combines bag-of-words features and automatically generated sequence-based features. Our results show that combining automatically and manually crafted features fed into a neural architecture outperform transfer learning approach on more unbalanced datasets.
%R 10.18653/v1/S19-2108
%U https://aclanthology.org/S19-2108
%U https://doi.org/10.18653/v1/S19-2108
%P 604-610
Markdown (Informal)
[Embeddia at SemEval-2019 Task 6: Detecting Hate with Neural Network and Transfer Learning Approaches](https://aclanthology.org/S19-2108) (Pelicon et al., SemEval 2019)
ACL