English

Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement

Computation and Language 2021-03-22 v2 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2003.13118,
  title  = {Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement},
  author = {Alireza Mohammadshahi and James Henderson},
  journal= {arXiv preprint arXiv:2003.13118},
  year   = {2021}
}

Comments

Accepted to Transactions of the Association for Computational Linguistics (TACL) journal

R2 v1 2026-06-23T14:31:04.826Z