Graph-to-Graph Transformer for Transition-based Dependency Parsing
share
Transition-based dependency parsing is a challenging task for conditioning on and predicting structures. We demonstrate state-of-the-art results on this benchmark with the Graph2Graph Transformer architecture. This novel architecture supports both the input and output of arbitrary graphs via its attention mechanism. It can also be integrated both with previous neural network structured prediction techniques and with existing Transformer pre-trained models. Both with and without BERT pretraining, adding dependency graph inputs via the attention mechanism results in significant improvements over previously proposed mechanism for encoding the partial parse tree, resulting in accuracies which improve the state-of-the-art in transition-based dependency parsing, achieving 95.64 WSJ dependencies. Graph2Graph Transformers are not restricted to tree structures and can be easily applied to a wide range of NLP tasks.
READ FULL TEXT
