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

Alireza Mohammadshahi, James Henderson


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.
Anthology ID:
2021.tacl-1.8
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
120–138
Language:
URL:
https://aclanthology.org/2021.tacl-1.8
DOI:
10.1162/tacl_a_00358
Bibkey:
Cite (ACL):
Alireza Mohammadshahi and James Henderson. 2021. Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement. Transactions of the Association for Computational Linguistics, 9:120–138.
Cite (Informal):
Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement (Mohammadshahi & Henderson, TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.8.pdf