Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training

In this paper, we propose second-order graph-based neural dependency parsing using message passing and end-to-end neural networks. We empirically show that our approaches match the accuracy of very recent state-of-the-art second-order graph-based neural dependency parsers and have significantly faster speed in both training and testing. We also empirically show the advantage of second-order parsing over first-order parsing and observe that the usefulness of the head-selection structured constraint vanishes when using BERT embedding.

PDF Abstract Asian Chapter 2020 PDF Asian Chapter 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Dependency Parsing Chinese Treebank MFVI LAS 91.69 # 1
UAS 92.78 # 1
Dependency Parsing Penn Treebank MFVI UAS 96.91 # 5
LAS 95.34 # 5

Methods