Abstract
We present PERIN, a novel permutationinvariant approach to sentence-to-graph semantic parsing. PERIN is a versatile, crossframework and language independent architecture for universal modeling of semantic structures. Our system participated in the CoNLL 2020 shared task, Cross-Framework Meaning Representation Parsing (MRP 2020), where it was evaluated on five different frameworks (AMR, DRG, EDS, PTG and UCCA) across four languages. PERIN was one of the winners of the shared task. The source code and pretrained models are available at http://www. github.com/ufal/perin.
Cite
CITATION STYLE
Samuel, D., & Straka, M. (2020). ÚFAL at MRP 2020: Permutation-invariant Semantic Parsing in PERIN. In CoNLL 2020 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2020 Shared Task: Cross-Framework Meaning Representation Parsing (pp. 53–64). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2020.conll-shared.5
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
