Svandiela @ HaSpeeDe:用BERT检测意大利推特数据中的仇恨言论(短文)

Svea Klaus, Anna-Sophie Bartle, Daniela Rossmann
{"title":"Svandiela @ HaSpeeDe:用BERT检测意大利推特数据中的仇恨言论(短文)","authors":"Svea Klaus, Anna-Sophie Bartle, Daniela Rossmann","doi":"10.4000/BOOKS.AACCADEMIA.7037","DOIUrl":null,"url":null,"abstract":"English. This paper explains the system developed for the Hate Speech Detection (HaSpeeDe) shared task within the 7th evaluation campaign EVALITA 2020 (Basile et al., 2020). The task solution proposed in this work is based on a fine-tuned BERT model. In cross-corpus evaluation, our model reached an F1 score of 77,56% on the tweets test set, and 60,31% on the news headlines test set. Italiano. Questo articolo spiega il sistema sviluppato per il tesk finalizzato all’individuazione dei discorsi d’odio all’interno della campagna di valutazione EVALITA 2020 (Basile et al., 2020). La soluzione proposta per il task è basata su un raffinemento di un modello BERT. Nella valutazione finale il nostro modello raggiunge un valore F1 di 77,56% sul dataset di tweets e di 60,31% sul dataset di titoli di giornale.","PeriodicalId":184564,"journal":{"name":"EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020","volume":"79 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Svandiela @ HaSpeeDe: Detecting Hate Speech in Italian Twitter Data with BERT (short paper)\",\"authors\":\"Svea Klaus, Anna-Sophie Bartle, Daniela Rossmann\",\"doi\":\"10.4000/BOOKS.AACCADEMIA.7037\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"English. This paper explains the system developed for the Hate Speech Detection (HaSpeeDe) shared task within the 7th evaluation campaign EVALITA 2020 (Basile et al., 2020). The task solution proposed in this work is based on a fine-tuned BERT model. In cross-corpus evaluation, our model reached an F1 score of 77,56% on the tweets test set, and 60,31% on the news headlines test set. Italiano. Questo articolo spiega il sistema sviluppato per il tesk finalizzato all’individuazione dei discorsi d’odio all’interno della campagna di valutazione EVALITA 2020 (Basile et al., 2020). La soluzione proposta per il task è basata su un raffinemento di un modello BERT. Nella valutazione finale il nostro modello raggiunge un valore F1 di 77,56% sul dataset di tweets e di 60,31% sul dataset di titoli di giornale.\",\"PeriodicalId\":184564,\"journal\":{\"name\":\"EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020\",\"volume\":\"79 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.4000/BOOKS.AACCADEMIA.7037\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4000/BOOKS.AACCADEMIA.7037","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

English。这份文件暴露了为仇恨言论探测(HaSpeeDe)开发的系统这项工作的建议是基于一个精细设计的伯特模型。在交叉形体评估中,我们的模型在推特测试集上的分数为77.56%,在新闻标题测试集上的分数为60.31%。意大利。这篇文章解释了在eveta 2020评估运动中为tesk开发的仇恨言论识别系统(Basile et al., 2020)。工作组提出的解决方案是基于改进BERT模型。在最终评估中,我们的模型在推特dataset上的F1值为77.56%,在新闻标题dataset上的F1值为60.31%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Svandiela @ HaSpeeDe: Detecting Hate Speech in Italian Twitter Data with BERT (short paper)
English. This paper explains the system developed for the Hate Speech Detection (HaSpeeDe) shared task within the 7th evaluation campaign EVALITA 2020 (Basile et al., 2020). The task solution proposed in this work is based on a fine-tuned BERT model. In cross-corpus evaluation, our model reached an F1 score of 77,56% on the tweets test set, and 60,31% on the news headlines test set. Italiano. Questo articolo spiega il sistema sviluppato per il tesk finalizzato all’individuazione dei discorsi d’odio all’interno della campagna di valutazione EVALITA 2020 (Basile et al., 2020). La soluzione proposta per il task è basata su un raffinemento di un modello BERT. Nella valutazione finale il nostro modello raggiunge un valore F1 di 77,56% sul dataset di tweets e di 60,31% sul dataset di titoli di giornale.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
DIACR-Ita @ EVALITA2020: Overview of the EVALITA2020 Diachronic Lexical Semantics (DIACR-Ita) Task QMUL-SDS @ DIACR-Ita: Evaluating Unsupervised Diachronic Lexical Semantics Classification in Italian (short paper) By1510 @ HaSpeeDe 2: Identification of Hate Speech for Italian Language in Social Media Data (short paper) HaSpeeDe 2 @ EVALITA2020: Overview of the EVALITA 2020 Hate Speech Detection Task KIPoS @ EVALITA2020: Overview of the Task on KIParla Part of Speech Tagging
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1