Multilingual BERT (mBERT) has demonstrated considerable cross-lingual
syntactic ability, whereby it enables effective zero-shot cross-lingual
transfer of syntactic knowledge. The transfer is more successful between some
languages, but it is not well understood what leads to this variation and
whether it fairly reflects difference between languages. In this work, we
investigate the distributions of grammatical relations induced from mBERT in
the context of 24 typologically different languages. We demonstrate that the
distance between the distributions of different languages is highly consistent
with the syntactic difference in terms of linguistic formalisms. Such
difference learnt via self-supervision plays a crucial role in the zero-shot
transfer performance and can be predicted by variation in morphosyntactic
properties between languages. These results suggest that mBERT properly encodes
languages in a way consistent with linguistic diversity and provide insights
into the mechanism of cross-lingual transfer.

该论文研究了多语言 BERT（mBERT）对 24 种不同语言的语法关系的分布，发现该分布与语言形式差异高度一致，提示 mBERT 以与语言多样性一致的方式正确编码语言，并揭示了跨语言传输机制的内在机理。

多语言 BERT 中的跨语言句法差异：好不好及其对迁移的影响？

Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?

We describe a recently developed corpus annotation scheme for evaluating
parsers that avoids shortcomings of current methods. The scheme encodes
grammatical relations between heads and dependents, and has been used to mark
up a new public-domain corpus of naturally occurring English text. We show how
the corpus can be used to evaluate the accuracy of a robust parser, and relate
the corpus to extant resources.

通过语料库标注方案与英文文本标注，我们描述了一种避免当前方法的缺点的解析器评估方法，并展示了该语料库如何用于评估健壮的解析器，以及与现有资源的关系。

用于解析器评估的语料库标注

Corpus Annotation for Parser Evaluation

In this paper we discuss cascaded Memory-Based grammatical relations
assignment. In the first stages of the cascade, we find chunks of several types
(NP,VP,ADJP,ADVP,PP) and label them with their adverbial function (e.g. local,
temporal). In the last stage, we assign grammatical relations to pairs of
chunks. We studied the effect of adding several levels to this cascaded
classifier and we found that even the less performing chunkers enhanced the
performance of the relation finder.

本文探讨了级联的基于记忆的语法关系分类器，并研究了向该分类器添加多个级别的效果，发现即使是表现较差的切块器也可以提高关系查找器的性能。