We propose the Recursive Non-autoregressive Graph-to-Graph Transformer
architecture (RNGTr) for the iterative refinement of arbitrary graphs through
the recursive application of a non-autoregressive Graph-to-Graph Transformer
and apply it to syntactic dependency parsing. We demonstrate the power and
effectiveness of RNGTr on several dependency corpora, using a refinement model
pre-trained with BERT. We also introduce Syntactic Transformer (SynTr), a
non-recursive parser similar to our refinement model. RNGTr can improve the
accuracy of a variety of initial parsers on 13 languages from the Universal
Dependencies Treebanks, English and Chinese Penn Treebanks, and the German
CoNLL2009 corpus, even improving over the new state-of-the-art results achieved
by SynTr, significantly improving the state-of-the-art for all corpora tested.

本文提出了一种基于递归非自回归图到图变换器 (RNGTr) 的架构，用于任意图的迭代细化，通过应用非自回归图到图变换器的递归应用，并将其应用于句法依赖解析上。我们使用使用 BERT 预训练的细化模型展示了 RNGTr 的强大和有效性。我们还介绍了一款类似于我们优化模型的非递归解析器 Syntactic Transformer (SynTr)。RNGTr 可以提高 13 种语言的各种初始解析器的准确性，包括 Universal Dependencies Treebanks，英语和中文 Penn Treebanks，以及德语 CoNLL2009 语料库，并且在所有测试数据上显著超越了最新的最优结果的表现。