Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement
This work addresses syntactic dependency parsing for natural language processing, offering incremental improvements over existing methods.
The authors tackled the problem of syntactic dependency parsing by proposing the Recursive Non-autoregressive Graph-to-Graph Transformer (RNGTr) for iterative graph refinement, which improved accuracy over various initial parsers and achieved new state-of-the-art results on multiple dependency corpora.
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.