论文标题
交叉中和：探测多语言模型中语言信息的联合编码
Cross-neutralising: Probing for joint encoding of linguistic information in multilingual models
论文作者
论文摘要
多语言句子编码器被广泛用于跨语言传输NLP模型。但是，这种转移的成功取决于模型编码跨语言相似性和变化模式的能力。然而，这些模型如何能够做到这一点，鲜为人知。我们提出了一种简单的方法来研究如何在两个最先进的多语言模型（即M-bert和XLM-R）中编码语言之间的关系。结果提供了有关其信息共享机制的洞察力，并表明语言特性是在这些模型中类型相似的语言中共同编码的。
Multilingual sentence encoders are widely used to transfer NLP models across languages. The success of this transfer is, however, dependent on the model's ability to encode the patterns of cross-lingual similarity and variation. Yet, little is known as to how these models are able to do this. We propose a simple method to study how relationships between languages are encoded in two state-of-the-art multilingual models (i.e. M-BERT and XLM-R). The results provide insight into their information sharing mechanisms and suggest that linguistic properties are encoded jointly across typologically-similar languages in these models.
