ShanghaiTech在MRP 2019：跨框架意义表示解析的序列到图转换与二阶边推理
ShanghaiTech at MRP 2019: Sequence-to-Graph Transduction with Second-Order Edge Inference for Cross-Framework Meaning Representation Parsing
摘要：
本文介绍了我们提交给\textit{CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing}的系统。我们的系统是一个基于图形的解析器，它结合了一个扩展的指针生成器网络，生成节点和一个二阶平均场变分推理模块，预测边缘。我们的系统实现了\nth{1}和\nth{2}的地方，分别为DM和PSD框架上的框架行列，并实现了\nth{3}地方的DM框架上的跨框架行列。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
