We present PERIN, a novel permutation-invariant approach to sentence-to-graph semantic parsing. PERIN is a versatile, cross-framework 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 https://github.com/ufal/perin.
翻译:我们介绍了PERIN, 这是一种新颖的从变式到文字语义拼法的方法,PERIN是通用语义结构建模的多功能、跨框架和语言独立结构,我们的系统参与了CONLL 2020 共同任务,跨框架代表分析(MRP 2020),在其中对四种语言的五个不同框架(AMR、DRG、EDS、PTG和UCCA)进行了评估,PERIN是共同任务的优胜者之一,源代码和预先培训的模式见https://github.com/ufal/perin。