Abstract
This paper describes our system (RESOLVER) submitted to the CoNLL 2019 shared task on Cross-Framework Meaning Representation Parsing (MRP). Our system implements a transition-based parser with a directed acyclic graph (DAG) to tree preprocessor and a novel cross-framework variable-arity resolve action that generalizes over five different representations. Although we ranked low in the competition, we have shown the current limitations and potentials of including variable-arity action in MRP and concluded with directions for improvements in the future.- Anthology ID:
- K19-2010
- 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:
- 104–113
- Language:
- URL:
- https://aclanthology.org/K19-2010
- DOI:
- 10.18653/v1/K19-2010
- Cite (ACL):
- Sunny Lai, Chun Hei Lo, Kwong Sak Leung, and Yee Leung. 2019. CUHK at MRP 2019: Transition-Based Parser with Cross-Framework Variable-Arity Resolve Action. In Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning, pages 104–113, Hong Kong. Association for Computational Linguistics.
- Cite (Informal):
- CUHK at MRP 2019: Transition-Based Parser with Cross-Framework Variable-Arity Resolve Action (Lai et al., CoNLL 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/K19-2010.pdf