We investigate whether off-the-shelf deep bidirectional sentence
representations trained on a massively multilingual corpus (multilingual BERT)
enable the development of an unsupervised universal dependency parser. This
approach only leverages a mix of monolingual corpora in many languages and does
not require any translation data making it applicable to low-resource
languages. In our experiments we outperform the best CoNLL 2018
language-specific systems in all of the shared task's six truly low-resource
languages while using a single system. However, we also find that (i) parsing
accuracy still varies dramatically when changing the training languages and
(ii) in some target languages zero-shot transfer fails under all tested
conditions, raising concerns on the 'universality' of the whole approach.

本篇论文研究了是否可以利用大规模多语言语料库（multilingual BERT）上预训练的现成双向深度句子表征，开发出一种无监督的通用句法分析器，以支持低资源语言的处理。实验结果表明，我们的方法在六种真正的低资源语言中均优于 CoNLL 2018 语言特定系统，但仍存在一些限制，如句法分析精度仍然随训练语言的变化而变化，并且在某些目标语言中，零 - shot 转移在所有测试条件下都无法成功，这引发了人们对整个方法的普适性问题的担忧。