Bootstrapping Multilingual AMR with Contextual Word Alignments
This work provides improved multilingual AMR systems, which is significant for researchers and applications requiring semantic representation across multiple languages.
This paper developed high-performance multilingual Abstract Meaning Representation (AMR) systems by projecting English AMR annotations to other languages using weakly supervised contextual word alignments. The resulting systems surpassed the best published results for German, Italian, Spanish, and Chinese.
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.