SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification
IBM Research(IBM研究);University of Copenhagen(哥本哈根大学);University of Cambridge(剑桥大学);Rochester Institute of Technology(罗切斯特理工学院);Qatar Computing Research Institute, HBKU(卡塔尔计算研究学院,哈马德·本·哈利法大学)
Sara Rosenthal, Pepa Atanasova, Georgi Karadzhov, Marcos Zampieri, Preslav Nakov
备注:
offensive language, hate speech, cyberbullying, cyber-aggression, taxonomy for offensive language identification
The widespread use of offensive content in social media has led to an abundance of research in detecting language such as hate speech, cyberbullying, and cyber-aggression. Recent work presented the OLID dataset, which follows a taxonomy for offensive language identification that provides meaningful information for understanding the type and the target of offensive messages. However, it is limited in size and it might be biased towards offensive language as it was collected using keywords. In this work, we present SOLID, an expanded dataset, where the tweets were collected in a more principled manner. SOLID contains over nine million English tweets labeled in a semi-supervised fashion. We demonstrate that using SOLID along with OLID yields sizable performance gains on the OLID test set for two different models, especially for the lower levels of the taxonomy.
Predicting the Type and Target of Offensive Posts in Social Media
University of Wolverhampton(伍尔弗汉普顿大学);Harvard Medical School(哈佛医学院);Qatar Computing Research Institute, HBKU(哈马德·本·哈利法大学卡塔尔计算研究所);IBM Research(IBM研究院);Columbia University(哥伦比亚大学);Bhim Rao Ambedkar University(比姆·拉奥·安贝德卡尔大学)
A simple language-agnostic yet very strong baseline system for hate speech and offensive content identification
Laboratoire d’analyse statistique des textes - Statistical Analysis of Text Laboratory (LAST - SATLab)(文本统计分析实验室(LAST - SATLab));Institut de recherche en sciences psychologiques(心理科学研究所);Université catholique de Louvain(鲁汶天主教大学)
Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages
University of Hildesheim(希尔德斯海姆大学);LDRP-ITR;University of Duisburg-Essen(杜伊斯堡-埃森大学);Indian Institute of Science(印度科学理工学院);DA-IICT;University of Wolverhampton(伍尔弗汉普顿大学);Rochester Institute of Technology(罗切斯特理工学院);University of Bamberg(班贝格大学);University of Bedfordshire(贝德福德大学);University of Leeds(利兹大学)
仇恨言论等攻击性内容在网上的广泛传播构成了日益严重的社会问题。人工智能工具对于支持在线平台的审核过程是必要的。为了评估这些识别工具,需要对不同语言的数据集进行连续实验。HASOC(Hate Speech and Offensive Content Identification,仇恨言论和攻击性内容识别)专门为此目的开发基准数据。本文介绍了英语,印地语和马拉地语的HASOC子轨道。该数据集来自Twitter。此子路径有两个子任务。任务A是针对所有三种语言的二元分类问题(仇恨和不冒犯)。任务B是一个细粒度的分类问题,分为三类(仇恨)仇恨言论,进攻和专业提供的英语和印地语。总共有65支球队提交了652次跑步。任务A的最佳分类算法的性能是F1措施0.91,0.78和0.83马拉地语,印地语和英语,分别。本概述介绍了任务和数据开发以及详细结果。提交竞赛的系统应用了各种技术。性能最好的算法主要是Transformer架构的变体。
QutNocturnal@HASOC'19: CNN for Hate Speech and Offensive Content Identification in Hindi Language
Queensland University of Technology(昆士兰科技大学)
我们描述了我们在FIRE 2019组织的HASOC竞赛中为印地语任务1提供的顶级团队解决方案。任务是识别印地语中的仇恨言论和攻击性语言。更具体地说,这是一个二元分类问题,其中需要系统将推文分类为两类:(a)\emph{Hate and Offensive (HOF)}和(b)\emph{Not Hate or Offensive (NOT)}。与流行的预训练词向量(也称为词嵌入)与来自维基百科等通用领域的大型语料库,我们使用相对较小的相关推文集合(即印地语和印度英语的随机和讽刺推文)进行预训练。我们在预训练的词向量之上训练了一个卷积神经网络(CNN)。这种方法使我们在所有团队中排名第一。我们的方法可以很容易地适应其他应用程序的目标是预测类的文本时,所提供的上下文是有限的。
Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languages
University of Hildesheim(希尔德斯海姆大学);LDRP-ITR;University of Duisburg-Essen(杜伊斯堡-埃森大学);University of Bedfordshire(贝德福德大学);University of Leeds(利兹大学);University of Bamberg(班贝格大学);Dalhousie University(达尔豪斯大学);DA-IICT
Aston University(阿斯顿大学);University of Wolverhampton(伍尔弗汉普顿大学);Birmingham City University(伯明翰城市大学);University of Münster(明斯特大学);George Mason University(乔治梅森大学)
Findings of the Shared Task on Offensive Span Identification from Code-Mixed Tamil-English Comments
Georgia Institute of Technology(佐治亚理工学院);Data Science Institute, National University of Ireland Galway(爱尔兰国立高威大学数据科学研究所);National Institute of Technology Karnataka Surathkal(卡纳塔克邦苏拉特卡尔国家理工学院);National Institute of Technology, Trichy(特里奇国家理工学院);Vellore Institute of Technology(韦洛尔理工学院);Eastern University, Sri Lanka(斯里兰卡东方大学);Indian Institute of Information Technology and Management, Kerala(喀拉拉邦印度信息技术与管理学院);Thiagarajar College of Engineering(蒂亚加拉贾工程学院)
KBCNMUJAL@HASOC-Dravidian-CodeMix-FIRE2020: Using Machine Learning for Detection of Hate Speech and Offensive Code-Mixed Social Media text
Institute of Management and Research, Jalgaon, Affil- KBC North Maharashtra University(贾尔冈管理与研究学院,隶属于KBC北马哈拉施特拉大学);School of Computer Sciences, KBC North Maharashtra University(KBC北马哈拉施特拉大学计算机科学学院);Copenhagen Business School(哥本哈根商学院);BMCC college of commerce, Pune(BMCC商学院,浦那)
Developing Successful Shared Tasks on Offensive Language Identification for Dravidian Languages
Insight SFI Research Centre for Data Analytics, National University of Ireland Galway(爱尔兰国立大学戈尔韦分校Insight数据分析研究中心);TR Labs, Thomson Reuters(汤森路透TR实验室);ULTRA Arts and Science College(ULTRA文理学院);National Institute of Technology Karnataka Surathkal(卡纳塔克邦苏拉特卡尔国立技术学院);Eastern University(东方大学);National Institute of Technology Tiruchirappalli(蒂鲁吉拉帕利国立技术学院);SRM Institute of Science and Technology(SRM科学技术学院)
SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)
Rochester Institute of Technology(罗切斯特理工学院);Qatar Computing Research Institute(卡塔尔计算研究所);IBM Research(IBM研究院);University of Copenhagen(哥本哈根大学);University of Cambridge(剑桥大学);IT University Copenhagen(哥本哈根信息技术大学);University of Wolverhampton(伍尔弗汉普顿大学);University of Tübingen(图宾根大学)
DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text
National University of Ireland Galway(爱尔兰国立大学戈尔韦分校);ULTRA Arts and Science College(ULTRA艺术与科学学院);Cardiff University(卡迪夫大学);Indian Institute of Information Technology and Management-Kerala(印度喀拉拉邦信息技术与管理学院)
Zero-shot Code-Mixed Offensive Span Identification through Rationale Extraction
Georgia Institute of Technology(佐治亚理工学院);Data Science Institute, National University of Ireland Galway(爱尔兰国立高威大学数据科学研究所)
本文探讨了有效性的代码混合泰米尔语数据集上的zero-shot攻击跨度识别的双电平Transformers。更具体地说,我们评估合理的本地可解释模型不可知推理(LIME)\cite{DBLP:conf/kdd/Ribeiro0G16}和综合推理(IG)\cite{DBLP:conf/icml/SundararajanTY17}适应Transformer为基础的攻击性语言分类模型的zero-shot进攻跨度识别的提取方法。为此,我们发现LIME和IG显示基线$F_{1}$分别为26.35%和44.83%。此外,我们研究了数据集大小和训练过程对跨度识别整体准确性的影响。因此,我们发现LIME和IG在掩蔽数据增强和多标签训练中表现出显着的改善,$F_{1}$分别为50.23%和47.38%。\textit{Disclaimer : This paper contains examples that may be considered profane, vulgar, or offensive. The examples do not represent the views of the authors or their employers/graduate schools towards any person(s), group(s), practice(s), or entity/en…
WOLI at SemEval-2020 Task 12: Arabic Offensive Language Identification on Different Twitter Datasets
WideBot(宽博科技(WideBot))
通过社交平台进行沟通已成为个人沟通和互动的主要手段之一。不幸的是,健康的沟通经常受到攻击性语言的干扰,这可能对用户产生破坏性影响。在社交媒体上打击攻击性语言的关键是存在自动攻击性语言检测系统。本文介绍了SemEval-2020的结果和主要发现,任务12 OffensEval子任务A Zampieri et al.(2020),关于识别和分类社交媒体中的攻击性语言。该任务基于阿拉伯语OffensEval数据集Mubarak et al.(2020)。在本文中,我们描述了WideBot AI Lab提交的共享任务系统,该系统在CodaLab用户名为“yasserotiefy”的黄金数据集上,在52名参与者中排名第10位,Macro-F1为86.9%。我们实验了各种模型,最好的模型是线性SVM,其中我们使用字符和单词n-gram的组合。我们还引入了一种神经网络方法,增强了我们系统的预测能力,包括CNN、高速公路网络、Bi-LSTM和注意力层。
Offensive Language Identification in Low-resourced Code-mixed Dravidian languages using Pseudo-labeling
Indian Institute of Information Technology Tiruchirappalli(蒂鲁奇拉帕利印度信息技术学院);ULTRA Arts and Science College(ULTRA文理学院);Eastern University(东方大学);Kongu Engineering College(孔古工程学院);Sri Sivasubramaniya Nadar College of Engineering(斯里·西瓦苏布拉马尼亚·纳达尔工程学院);Insight SFI Research Centre for Data Analytics, National University of Ireland Galway(爱尔兰国立大学戈尔韦分校SFI洞察数据分析研究中心)