arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.01261cs.CL

社交媒体文本中仇恨言论到非仇恨言论的自动翻译

Automatic Translation of Hate Speech to Non-hate Speech in Social Media Texts

Instituto Politécnico Nacional(国立理工学院)

Yevhen Kostiuk, Atnafu Lambebo Tonja, Grigori Sidorov, Olga Kolesnikova

AI总结:

本文提出将西班牙语仇恨言论在保留原意的前提下自动改写为非仇恨言论的新任务,并提供数据集与多个基线,采用 BLEU 等指标评估,以助力遏制在线仇恨言论传播。

摘要:

本文研究仇恨言论问题,提出了一项新任务:在保留原意的同时,将仇恨言论翻译为非仇恨言论文本。作为案例研究,我们使用西班牙语文本。我们提供了一个数据集和若干基线,作为该任务进一步研究的起点。我们使用包括 BLEU 分数在内的多种指标评估了基线结果。本研究旨在推动开发更有效的方法,以减少仇恨言论在在线社区中的传播。

英文摘要:

In this paper, we investigate the issue of hate speech by presenting a novel task of translating hate speech into non-hate speech text while preserving its meaning. As a case study, we use Spanish texts. We provide a dataset and several baselines as a starting point for further research in the task. We evaluated our baseline results using multiple metrics, including BLEU scores. The aim of this study is to contribute to the development of more effective methods for reducing the spread of hate speech in online communities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑