Towards a Catalogue of Linguistic Graph Banks

Meaning Representation (AMR). Unlike the bilexical dependency graphs of CCD, DM, and PSD, AMR eschews explicit syntactic derivations and consideration of the syntax–semantics interface; it rather seeks to directly annotate “whole-sentence logical meanings” (Banarescu et al. 2013). Node labels in AMR name abstract concepts, which in large part draw on the ontology of OntoNotes predicate senses and corresponding semantic roles. Nodes are not overtly related to surface lexical units, and thus are unordered. Although AMR has its roots in semantic networks and earlier knowledge representation approaches (Langkilde and Knight 1998), largerscale manual AMR annotation is a recent development only. We sample two variants of AMR, viz. (a) the graphs as annotated in AMRBank 1.0 (LDC2014 T12), and (b) a normalized version that we call AMR−1, where so-called “inverse roles” (like ARG0-of) are reversed. Such inverted edges are frequently used in AMR in order to render the graph as a single rooted structure, where the root is interpreted as the top-level focus.1 In Section 3, we map this interpretation to our concept of top nodes for both AMR and AMR−1. Flanigan et al. (2014) published the first parser targeting AMR, and the state of the art has been repeatedly updated since. 1 The graph bank is natively constructed and released with inverted edges, but for parser evaluation the AMR−1 normalization is typically assumed; our conversion builds on the code of Cai and Knight (2013).