Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement
| Type of publication: | Journal paper |
| Citation: | Mohammadshahi_TACL_2021 |
| Publication status: | Accepted |
| Journal: | Transactions of the Association for Computational Linguistics (2021) |
| Volume: | 9 |
| Year: | 2021 |
| Month: | March |
| Pages: | 18 |
| Crossref: | Mohammadshahi_TACL_2020: |
| URL: | https://direct.mit.edu/tacl/ar... |
| DOI: | https://doi.org/10.1162/tacl_a_00358 |
| 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: | |
| Projects |
Idiap Intrepid |
| Authors | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
