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 offence. 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.

本文介绍了使用 SyLSTM 来检测 Twitter 上的冒犯性言论，同时检测冒犯的类型和目标的新方法，该方法在深度学习体系结构中将句子的句法特征和语义特征相结合，通过图形卷积网络进行集成。结果表明，该方法在参数数量方面比最先进的 BERT 模型有数量级的优势。

基于依存语法的细粒度攻击性语言检测：使用图卷积网络

Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks

The increasing accessibility of the internet facilitated social media usage
and encouraged individuals to express their opinions liberally. Nevertheless,
it also creates a place for content polluters to disseminate offensive posts or
contents. Most of such offensive posts are written in a cross-lingual manner
and can easily evade the online surveillance systems. This paper presents an
automated system that can identify offensive text from multilingual code-mixed
data. In the task, datasets provided in three languages including Tamil,
Malayalam and Kannada code-mixed with English where participants are asked to
implement separate models for each language. To accomplish the tasks, we
employed two machine learning techniques (LR, SVM), three deep learning (LSTM,
LSTM+Attention) techniques and three transformers (m-BERT, Indic-BERT, XLM-R)
based methods. Results show that XLM-R outperforms other techniques in Tamil
and Malayalam languages while m-BERT achieves the highest score in the Kannada
language. The proposed models gained weighted $f_1$ score of $0.76$ (for
Tamil), $0.93$ (for Malayalam), and $0.71$ (for Kannada) with a rank of
$3^{rd}$, $5^{th}$ and $4^{th}$ respectively.

本论文提出了一种多语言自动化系统，使用机器学习和转换器来从混合语言的数据中识别带有冒犯性的文本，并在 Tamil、Malayalam 和 Kannada 三种语言的数据集上进行了测试。结果表明，该系统在不同语言上表现出不同的最佳表现方法，得分最高的是 m-BERT（Kannada）和 XLM-R（Tamil 和 Malayalam），系统性能达到了一定的水平。