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
- 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
- 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)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2021.tacl-1.8.pdf