Graph-based Dependency Parsing with Graph Neural Networks

ACL 2019  ·  Tao Ji, Yuanbin Wu, Man Lan ·

We investigate the problem of efficiently incorporating high-order features into neural graph-based dependency parsing. Instead of explicitly extracting high-order features from intermediate parse trees, we develop a more powerful dependency tree node representation which captures high-order information concisely and efficiently. We use graph neural networks (GNNs) to learn the representations and discuss several new configurations of GNN{'}s updating and aggregation functions. Experiments on PTB show that our parser achieves the best UAS and LAS on PTB (96.0{\%}, 94.3{\%}) among systems without using any external resources.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Dependency Parsing Penn Treebank Graph-based parser with GNNs POS 97.3 # 5
UAS 95.97 # 12
LAS 94.31 # 12


No methods listed for this paper. Add relevant methods here