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

arXiv: https://arxiv.org/abs/2004.03849 · HTML: https://mlsanity.com/paper/2004.03849/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2020.

## Built on by (most cited first, 1 of 1)

- [Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing](https://mlsanity.com/paper/2110.00621/) (2021)

## Abstract (arXiv)

This paper presents the system used in our submission to the textitCoNLL 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 nth1 and nth2 place for the DM and PSD frameworks respectively on the in-framework ranks and achieved nth3 place for the DM framework on the cross-framework ranks.