BriefGPT.xyz
May, 2018
跨语言性别预测的抽象特征与文本漂白
Bleaching Text: Abstract Features for Cross-lingual Gender Prediction
HTML
PDF
Rob van der Goot, Nikola Ljubešić, Ian Matroos, Malvina Nissim, Barbara Plank
TL;DR
通过使用抽象特征代替传统的词汇文本，可以提高性别预测在不同语言之间的迁移性能，而这种基于抽象特征的预测方法人类的预测能力不比传统方法差，并且优于词汇模型。
Abstract
gender prediction
has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent.
cross-lingual embeddings
circumvent
→