Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement
- ID: 20231012155320260-1322
- Researcher: Alireza Mohammadshahi, James Henderson
- WP: Other
- PI: 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.
- Publication DOI: https://doi.org/10.1162/tacl_a_00358
- Publication Link: https://doi.org/10.1162/tacl_a_00358
- Data Type: null
- Data Format: null
- Data Link: https://github.com/idiap/g2g-transformer
- Git: None
Last modified: le 2023/10/16 12:11