@inproceedings{aglionby-etal-2019-camsterdam,
title = "{CAM}sterdam at {S}em{E}val-2019 Task 6: Neural and graph-based feature extraction for the identification of offensive tweets",
author = "Aglionby, Guy and
Davis, Chris and
Mishra, Pushkar and
Caines, Andrew and
Yannakoudakis, Helen and
Rei, Marek and
Shutova, Ekaterina and
Buttery, Paula",
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/S19-2100",
doi = "10.18653/v1/S19-2100",
pages = "556--563",
abstract = "We describe the CAMsterdam team entry to the SemEval-2019 Shared Task 6 on offensive language identification in Twitter data. Our proposed model learns to extract textual features using a multi-layer recurrent network, and then performs text classification using gradient-boosted decision trees (GBDT). A self-attention architecture enables the model to focus on the most relevant areas in the text. In order to enrich input representations, we use node2vec to learn globally optimised embeddings for hashtags, which are then given as additional features to the GBDT classifier. Our best model obtains 78.79{\%} macro F1-score on detecting offensive language (subtask A), 66.32{\%} on categorising offence types (targeted/untargeted; subtask B), and 55.36{\%} on identifying the target of offence (subtask C).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aglionby-etal-2019-camsterdam">
<titleInfo>
<title>CAMsterdam at SemEval-2019 Task 6: Neural and graph-based feature extraction for the identification of offensive tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Aglionby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Davis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushkar</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Caines</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Buttery</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>We describe the CAMsterdam team entry to the SemEval-2019 Shared Task 6 on offensive language identification in Twitter data. Our proposed model learns to extract textual features using a multi-layer recurrent network, and then performs text classification using gradient-boosted decision trees (GBDT). A self-attention architecture enables the model to focus on the most relevant areas in the text. In order to enrich input representations, we use node2vec to learn globally optimised embeddings for hashtags, which are then given as additional features to the GBDT classifier. Our best model obtains 78.79% macro F1-score on detecting offensive language (subtask A), 66.32% on categorising offence types (targeted/untargeted; subtask B), and 55.36% on identifying the target of offence (subtask C).</abstract>
<identifier type="citekey">aglionby-etal-2019-camsterdam</identifier>
<identifier type="doi">10.18653/v1/S19-2100</identifier>
<location>
<url>https://aclanthology.org/S19-2100</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>556</start>
<end>563</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAMsterdam at SemEval-2019 Task 6: Neural and graph-based feature extraction for the identification of offensive tweets
%A Aglionby, Guy
%A Davis, Chris
%A Mishra, Pushkar
%A Caines, Andrew
%A Yannakoudakis, Helen
%A Rei, Marek
%A Shutova, Ekaterina
%A Buttery, Paula
%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 aglionby-etal-2019-camsterdam
%X We describe the CAMsterdam team entry to the SemEval-2019 Shared Task 6 on offensive language identification in Twitter data. Our proposed model learns to extract textual features using a multi-layer recurrent network, and then performs text classification using gradient-boosted decision trees (GBDT). A self-attention architecture enables the model to focus on the most relevant areas in the text. In order to enrich input representations, we use node2vec to learn globally optimised embeddings for hashtags, which are then given as additional features to the GBDT classifier. Our best model obtains 78.79% macro F1-score on detecting offensive language (subtask A), 66.32% on categorising offence types (targeted/untargeted; subtask B), and 55.36% on identifying the target of offence (subtask C).
%R 10.18653/v1/S19-2100
%U https://aclanthology.org/S19-2100
%U https://doi.org/10.18653/v1/S19-2100
%P 556-563
Markdown (Informal)
[CAMsterdam at SemEval-2019 Task 6: Neural and graph-based feature extraction for the identification of offensive tweets](https://aclanthology.org/S19-2100) (Aglionby et al., SemEval 2019)
ACL
- Guy Aglionby, Chris Davis, Pushkar Mishra, Andrew Caines, Helen Yannakoudakis, Marek Rei, Ekaterina Shutova, and Paula Buttery. 2019. CAMsterdam at SemEval-2019 Task 6: Neural and graph-based feature extraction for the identification of offensive tweets. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 556–563, Minneapolis, Minnesota, USA. Association for Computational Linguistics.