Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing

Yuta Koreeda, Gaku Morio, Terufumi Morishita, Hiroaki Ozaki, Kohsuke Yanai


Abstract
This paper describes the proposed system of the Hitachi team for the Cross-Framework Meaning Representation Parsing (MRP 2019) shared task. In this shared task, the participating systems were asked to predict nodes, edges and their attributes for five frameworks, each with different order of “abstraction” from input tokens. We proposed a unified encoder-to-biaffine network for all five frameworks, which effectively incorporates a shared encoder to extract rich input features, decoder networks to generate anchorless nodes in UCCA and AMR, and biaffine networks to predict edges. Our system was ranked fifth with the macro-averaged MRP F1 score of 0.7604, and outperformed the baseline unified transition-based MRP. Furthermore, post-evaluation experiments showed that we can boost the performance of the proposed system by incorporating multi-task learning, whereas the baseline could not. These imply efficacy of incorporating the biaffine network to the shared architecture for MRP and that learning heterogeneous meaning representations at once can boost the system performance.
Anthology ID:
K19-2011
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
Editors:
Stephan Oepen, Omri Abend, Jan Hajic, Daniel Hershcovich, Marco Kuhlmann, Tim O’Gorman, Nianwen Xue
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
114–126
Language:
URL:
https://aclanthology.org/K19-2011
DOI:
10.18653/v1/K19-2011
Bibkey:
Cite (ACL):
Yuta Koreeda, Gaku Morio, Terufumi Morishita, Hiroaki Ozaki, and Kohsuke Yanai. 2019. Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network 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 114–126, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing (Koreeda et al., CoNLL 2019)
Copy Citation:
PDF:
https://aclanthology.org/K19-2011.pdf