arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.03552cs.CLcs.AIcs.LGcs.NEcs.SI
收藏

低资源语言的跨语言攻击性语言识别:马拉地语案例

Cross-lingual Offensive Language Identification for Low Resource Languages: The Case of Marathi

Rochester Institute of Technology(罗切斯特理工学院);University of Wolverhampton(伍尔弗汉普顿大学)

Saurabh Gaikwad, Tharindu Ranasinghe, Marcos Zampieri, Christopher M. Homan

摘要:

攻击性语言在社交媒体上的广泛存在促使开发能够自动识别此类内容的系统。除了少数显著的例外,大多数关于自动攻击性语言识别的研究都涉及英语。为了解决这个缺点,我们引入了MOLD,马拉地语攻击性语言数据集。MOLD是为马拉地语编制的第一个此类数据集,从而为低资源的印度-雅利安语言的研究开辟了一个新的领域。我们在这个数据集上展示了几个机器学习实验的结果,包括零短路和其他迁移学习实验,这些实验是在孟加拉语、英语和印地语现有数据的最先进的跨语言Transformers上进行的。

英文摘要:

The widespread presence of offensive language on social media motivated the development of systems capable of recognizing such content automatically. Apart from a few notable exceptions, most research on automatic offensive language identification has dealt with English. To address this shortcoming, we introduce MOLD, the Marathi Offensive Language Dataset. MOLD is the first dataset of its kind compiled for Marathi, thus opening a new domain for research in low-resource Indo-Aryan languages. We present results from several machine learning experiments on this dataset, including zero-short and other transfer learning experiments on state-of-the-art cross-lingual transformers from existing data in Bengali, English, and Hindi.

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。

↑