@inproceedings{pavlopoulos-etal-2017-deeper,
title = "Deeper Attention to Abusive User Content Moderation",
author = "Pavlopoulos, John and
Malakasiotis, Prodromos and
Androutsopoulos, Ion",
editor = "Palmer, Martha and
Hwa, Rebecca and
Riedel, Sebastian",
booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D17-1117",
doi = "10.18653/v1/D17-1117",
pages = "1125--1135",
abstract = "Experimenting with a new dataset of 1.6M user comments from a news portal and an existing dataset of 115K Wikipedia talk page comments, we show that an RNN operating on word embeddings outpeforms the previous state of the art in moderation, which used logistic regression or an MLP classifier with character or word n-grams. We also compare against a CNN operating on word embeddings, and a word-list baseline. A novel, deep, classificationspecific attention mechanism improves the performance of the RNN further, and can also highlight suspicious words for free, without including highlighted words in the training data. We consider both fully automatic and semi-automatic moderation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pavlopoulos-etal-2017-deeper">
<titleInfo>
<title>Deeper Attention to Abusive User Content Moderation</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pavlopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prodromos</namePart>
<namePart type="family">Malakasiotis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ion</namePart>
<namePart type="family">Androutsopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Riedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Experimenting with a new dataset of 1.6M user comments from a news portal and an existing dataset of 115K Wikipedia talk page comments, we show that an RNN operating on word embeddings outpeforms the previous state of the art in moderation, which used logistic regression or an MLP classifier with character or word n-grams. We also compare against a CNN operating on word embeddings, and a word-list baseline. A novel, deep, classificationspecific attention mechanism improves the performance of the RNN further, and can also highlight suspicious words for free, without including highlighted words in the training data. We consider both fully automatic and semi-automatic moderation.</abstract>
<identifier type="citekey">pavlopoulos-etal-2017-deeper</identifier>
<identifier type="doi">10.18653/v1/D17-1117</identifier>
<location>
<url>https://aclanthology.org/D17-1117</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>1125</start>
<end>1135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deeper Attention to Abusive User Content Moderation
%A Pavlopoulos, John
%A Malakasiotis, Prodromos
%A Androutsopoulos, Ion
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F pavlopoulos-etal-2017-deeper
%X Experimenting with a new dataset of 1.6M user comments from a news portal and an existing dataset of 115K Wikipedia talk page comments, we show that an RNN operating on word embeddings outpeforms the previous state of the art in moderation, which used logistic regression or an MLP classifier with character or word n-grams. We also compare against a CNN operating on word embeddings, and a word-list baseline. A novel, deep, classificationspecific attention mechanism improves the performance of the RNN further, and can also highlight suspicious words for free, without including highlighted words in the training data. We consider both fully automatic and semi-automatic moderation.
%R 10.18653/v1/D17-1117
%U https://aclanthology.org/D17-1117
%U https://doi.org/10.18653/v1/D17-1117
%P 1125-1135
Markdown (Informal)
[Deeper Attention to Abusive User Content Moderation](https://aclanthology.org/D17-1117) (Pavlopoulos et al., EMNLP 2017)
ACL
- John Pavlopoulos, Prodromos Malakasiotis, and Ion Androutsopoulos. 2017. Deeper Attention to Abusive User Content Moderation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1125–1135, Copenhagen, Denmark. Association for Computational Linguistics.