BriefGPT.xyz
Jul, 2022
多语言变形金刚编码器：基于词级别的任务无关评估
Multilingual Transformer Encoders: a Word-Level Task-Agnostic Evaluation
HTML
PDF
Félix Gaschi, François Plesse, Parisa Rastin, Yannick Toussaint
TL;DR
本文提出一种单词级别的任务无关方法来评估多语言Transformers模型构建的上下文表示的对齐情况，并表明一些多语言Transformer模型的内部层表现优于其他明确对齐表示，甚至更符合更严格的多语言对齐定义。
Abstract
Some
transformer-based models
can perform
cross-lingual transfer learning
: those models can be trained on a specific task in one language and give relatively good results on the same task in another language, des
→