@inproceedings{goel-sharma-2022-leveraging,
title = "Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks",
author = "Goel, Divyam and
Sharma, Raksha",
editor = "Ku, Lun-Wei and
Li, Cheng-Te and
Tsai, Yu-Che and
Wang, Wei-Yao",
booktitle = "Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.socialnlp-1.4/",
doi = "10.18653/v1/2022.socialnlp-1.4",
pages = "45--54",
abstract = "The last few years have witnessed an exponential rise in the propagation of offensive text on social media. Identification of this text with high precision is crucial for the well-being of society. Most of the existing approaches tend to give high toxicity scores to innocuous statements (e.g., {\textquotedblleft}I am a gay man{\textquotedblright}). These false positives result from over-generalization on the training data where specific terms in the statement may have been used in a pejorative sense (e.g., {\textquotedblleft}gay{\textquotedblright}). Emphasis on such words alone can lead to discrimination against the classes these systems are designed to protect. In this paper, we address the problem of offensive language detection on Twitter, while also detecting the type and the target of the offense. We propose a novel approach called SyLSTM, which integrates syntactic features in the form of the dependency parse tree of a sentence and semantic features in the form of word embeddings into a deep learning architecture using a Graph Convolutional Network. Results show that the proposed approach significantly outperforms the state-of-the-art BERT model with orders of magnitude fewer number of parameters."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goel-sharma-2022-leveraging">
<titleInfo>
<title>Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Divyam</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raksha</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng-Te</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Che</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Yao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The last few years have witnessed an exponential rise in the propagation of offensive text on social media. Identification of this text with high precision is crucial for the well-being of society. Most of the existing approaches tend to give high toxicity scores to innocuous statements (e.g., “I am a gay man”). These false positives result from over-generalization on the training data where specific terms in the statement may have been used in a pejorative sense (e.g., “gay”). Emphasis on such words alone can lead to discrimination against the classes these systems are designed to protect. In this paper, we address the problem of offensive language detection on Twitter, while also detecting the type and the target of the offense. We propose a novel approach called SyLSTM, which integrates syntactic features in the form of the dependency parse tree of a sentence and semantic features in the form of word embeddings into a deep learning architecture using a Graph Convolutional Network. Results show that the proposed approach significantly outperforms the state-of-the-art BERT model with orders of magnitude fewer number of parameters.</abstract>
<identifier type="citekey">goel-sharma-2022-leveraging</identifier>
<identifier type="doi">10.18653/v1/2022.socialnlp-1.4</identifier>
<location>
<url>https://aclanthology.org/2022.socialnlp-1.4/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>45</start>
<end>54</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks
%A Goel, Divyam
%A Sharma, Raksha
%Y Ku, Lun-Wei
%Y Li, Cheng-Te
%Y Tsai, Yu-Che
%Y Wang, Wei-Yao
%S Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F goel-sharma-2022-leveraging
%X The last few years have witnessed an exponential rise in the propagation of offensive text on social media. Identification of this text with high precision is crucial for the well-being of society. Most of the existing approaches tend to give high toxicity scores to innocuous statements (e.g., “I am a gay man”). These false positives result from over-generalization on the training data where specific terms in the statement may have been used in a pejorative sense (e.g., “gay”). Emphasis on such words alone can lead to discrimination against the classes these systems are designed to protect. In this paper, we address the problem of offensive language detection on Twitter, while also detecting the type and the target of the offense. We propose a novel approach called SyLSTM, which integrates syntactic features in the form of the dependency parse tree of a sentence and semantic features in the form of word embeddings into a deep learning architecture using a Graph Convolutional Network. Results show that the proposed approach significantly outperforms the state-of-the-art BERT model with orders of magnitude fewer number of parameters.
%R 10.18653/v1/2022.socialnlp-1.4
%U https://aclanthology.org/2022.socialnlp-1.4/
%U https://doi.org/10.18653/v1/2022.socialnlp-1.4
%P 45-54
Markdown (Informal)
[Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks](https://aclanthology.org/2022.socialnlp-1.4/) (Goel & Sharma, SocialNLP 2022)
ACL