They are intended to abstract away from syntactic representations, in the sense that sentences which are similar in meaning should be assigned the same AMR, even if they are not identically worded.
Abstract Meaning Representations have originally been introduced by Langkilde and Knight (1998)[3] as a derivation from the Penman Sentence Plan Language,[4] they are thus continuing a long tradition in Natural Language Generation and this has been their original domain of application.
AMRs have re-gained attention since Banarescu et al. (2013),[1] in particular, this includes the extension to novel tasks such as machine translation and natural language understanding.
Existing AMR technology includes tools and libraries for parsing,[5] visualization,[6] and surface generation[7] as well as a considerable number of publicly available data sets.
In an extension of the original AMR formalism, Uniform Meaning Representations (UMR) have been proposed.