Understanding Social Biases Behind Location Names in Contextual Word Embedding Models
IEEE Transactions on Computational Social Systems(2022)
摘要
Embeddings of textual data containing location names (e.g., social media posts) have essential applications in various contexts such as marketing and disaster management. In these downstream implementations, social biases behind location names are highly prone to introduce unfair results through their embeddings; for example, emergent text messages with swapped location names might result in varie...
更多查看译文
关键词
Training data,Semantics,Task analysis,Training,Correlation,Bit error rate,Social networking (online)
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要