Recent analyses suggest that encoders pretrained for language modeling
capture certain morpho-syntactic structure. However, probing frameworks for
word vectors still do not report results on standard setups such as constituent
and dependency parsing. This paper addresses this problem and does full parsing
(on English) relying only on pretraining architectures -- and no decoding. We
first cast constituent and dependency parsing as sequence tagging. We then use
a single feed-forward layer to directly map word vectors to labels that encode
a linearized tree. This is used to: (i) see how far we can reach on syntax
modelling with just pretrained encoders, and (ii) shed some light about the
syntax-sensitivity of different word vectors (by freezing the weights of the
pretraining network during training). For evaluation, we use bracketing
F1-score and LAS, and analyze in-depth differences across representations for
span lengths and dependency displacements. The overall results surpass existing
sequence tagging parsers on the PTB (93.5%) and end-to-end EN-EWT UD (78.8%).

本文讨论了使用预训练架构（而非解码）进行单语种全刻度句法分析（成分和依赖）的问题，并使用序列标注作为模型，探讨了不同词向量的句法敏感性。实验分析显示，使用预训练编码器的结果优于现有序列标记解析器，F1 评分为 93.5％（PTB）和 78.8％（EN-EWT UD）的限制条件下。