ShanghaiTech at MRP 2019: Sequence-to-Graph Transduction with Second-Order Edge Inference for Cross-Framework Meaning Representation Parsing

04/08/2020

∙

by   Xinyu Wang, et al.

∙

0

∙

share

This paper presents the system used in our submission to the CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing. Our system is a graph-based parser which combines an extended pointer-generator network that generates nodes and a second-order mean field variational inference module that predicts edges. Our system achieved 1 and 2 place for the DM and PSD frameworks respectively on the in-framework ranks and achieved 3 place for the DM framework on the cross-framework ranks.