CLApr 8, 2020

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

arXiv:2004.03849v1997 citations
AI Analysis

This work addresses parsing challenges in natural language processing for researchers, but it is incremental as it builds on existing graph-based and inference methods.

The paper tackled cross-framework meaning representation parsing by developing a graph-based parser that combines an extended pointer-generator network for nodes and second-order mean field variational inference for edges, achieving first and second place in in-framework ranks and third place in cross-framework ranks.

This paper presents the system used in our submission to the \textit{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 \nth{1} and \nth{2} place for the DM and PSD frameworks respectively on the in-framework ranks and achieved \nth{3} place for the DM framework on the cross-framework ranks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes