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

Xinyu Wang, Yixian Liu, Zixia Jia, Chengyue Jiang, Kewei Tu


Abstract
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.
Anthology ID:
K19-2005
Volume:
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning
Month:
November
Year:
2019
Address:
Hong Kong
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
55–65
Language:
URL:
https://aclanthology.org/K19-2005
DOI:
10.18653/v1/K19-2005
Bibkey:
Cite (ACL):
Xinyu Wang, Yixian Liu, Zixia Jia, Chengyue Jiang, and Kewei Tu. 2019. ShanghaiTech at MRP 2019: Sequence-to-Graph Transduction with Second-Order Edge Inference for Cross-Framework Meaning Representation Parsing. In Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning, pages 55–65, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
ShanghaiTech at MRP 2019: Sequence-to-Graph Transduction with Second-Order Edge Inference for Cross-Framework Meaning Representation Parsing (Wang et al., CoNLL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/K19-2005.pdf
Code
 wangxinyu0922/Second_Order_SDP