pith. sign in

arxiv: 1805.09007 · v1 · pith:5MFWFPKOnew · submitted 2018-05-23 · 💻 cs.CL

A Transition-based Algorithm for Unrestricted AMR Parsing

classification 💻 cs.CL
keywords parsingalgorithmcyclesnon-projectivereentrancytransition-basedwhetherarbitrary
0
0 comments X
read the original abstract

Non-projective parsing can be useful to handle cycles and reentrancy in AMR graphs. We explore this idea and introduce a greedy left-to-right non-projective transition-based parser. At each parsing configuration, an oracle decides whether to create a concept or whether to connect a pair of existing concepts. The algorithm handles reentrancy and arbitrary cycles natively, i.e. within the transition system itself. The model is evaluated on the LDC2015E86 corpus, obtaining results close to the state of the art, including a Smatch of 64%, and showing good behavior on reentrant edges.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.