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

Published in Proceedings of CoNLL, 2019

pdf code bibtex

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 1st and 2nd place for the DM and PSD frameworks respectively on the in-framework ranks and achieved 3rd place for the DM framework on the cross-framework ranks.