We develop high performance multilingualAbstract Meaning Representation (AMR)
sys-tems by projecting English AMR annotationsto other languages with weak
supervision. Weachieve this goal by bootstrapping transformer-based
multilingual word embeddings, in partic-ular those from cross-lingual RoBERTa
(XLM-R large). We develop a novel technique forforeign-text-to-English AMR
alignment, usingthe contextual word alignment between En-glish and foreign
language tokens. This wordalignment is weakly supervised and relies onthe
contextualized XLM-R word embeddings.We achieve a highly competitive
performancethat surpasses the best published results forGerman, Italian,
Spanish and Chinese.

本研究通过弱监督的方法将英语的 AMR 注解与其他语言进行投射，使用跨语言的 RoBERTa (XLM-R large) 来引导多语言单词嵌入的投射过程，并使用一种新的技术来实现外文文本与英语 AMR 的对齐，通过上下文的单词对齐来弱监督跨语言 AMR 标注，实现了高性能的跨语言 AMR 标注。研究结果表明，本文方法在德语、意大利语、西班牙语和中文等四种语言上的表现已经超过了先前最好的实验结果。