人工智能培训

搜索

论文代码开源:深度微词典学习和编码网络(Deep Micro-Dictionary Learning and Coding Network)

[复制链接]
admin 发表于 2018-9-15 10:27:22 | 显示全部楼层 |阅读模式
admin 2018-9-15 10:27:22 1625 0 显示全部楼层
人工智能论文代码开源:深度微词典学习和编码网络(Deep Micro-Dictionary Learning and Coding Network)请注意该人工智能论文代码开源在github,大部分是python写的,框架可能是tensorflow或者pytorch。仇恨言论通常被定义为基于某些特征(例如种族,肤色,种族,性别,性取向,国籍,宗教或其他特征)贬低目标群体的任何沟通。随着社交媒体上用户生成的网络内容的大量增加,仇恨言论的数量也在稳步增加。在过去几年中,人们对仇恨言语检测的兴趣,尤其是这项任务的自动化,以及该现象的社会影响不断增长。本文描述了一种讨厌的语音数据集,该数据集由数千个句子组成,这些句子被标记为包含仇恨言论。这句话来自Stormfront,一个白人至上主义论坛。已经开发了一种自定义注释工具来执行手动标记任务,其中,其中,注释器允许注释器在标记之前选择是否读取句子的上下文。本文还对所得数据集进行了深思熟虑的定性和定量研究,并对不同分类模型进行了若干基线实验。数据集是公开可用的。
Hate speech is commonly defined as any communication that disparages a targetgroup of people based on some characteristic such as race, colour, ethnicity,gender, sexual orientation, nationality, religion, or other characteristic.Dueto the massive rise of user-generated web content on social media, the amountof hate speech is also steadily increasing.Over the past years, interest inonline hate speech detection and, particularly, the automation of this task hascontinuously grown, along with the societal impact of the phenomenon.Thispaper describes a hate speech dataset composed of thousands of sentencesmanually labelled as containing hate speech or not.The sentences have beenextracted from Stormfront, a white supremacist forum.A custom annotation toolhas been developed to carry out the manual labelling task which, among otherthings, allows the annotators to choose whether to read the context of asentence before labelling it.The paper also provides a thoughtful qualitativeand quantitative study of the resulting dataset and several baselineexperiments with different classification models.The dataset is publiclyavailable.论文代码开源:深度微词典学习和编码网络(Deep Micro-Dictionary Learning and Coding Network) v21QXHvqzIHRPiIq.jpg
URL地址:https://arxiv.org/abs/1809.04444v1     ----pdf下载地址:https://arxiv.org/pdf/1809.04444v1    ----         ----github下载地址:https://github.com/aitor-garcia-p/hate-speech-dataset    ----    论文代码开源:深度微词典学习和编码网络(Deep Micro-Dictionary Learning and Coding Network)请注意该人工智能论文代码开源在github,大部分是python写的,框架可能是tensorflow或者pytorch,keras,至于具体是哪一个没有完全测试。
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则 返回列表 发新帖

admin当前离线
管理员

查看:1625 | 回复:0

快速回复 返回顶部 返回列表