Factorising AMR generation through syntax
Computation and Language
2019-04-04 v2
Abstract
Generating from Abstract Meaning Representation (AMR) is an underspecified problem, as many syntactic decisions are not constrained by the semantic graph. To explicitly account for this underspecification, we break down generating from AMR into two steps: first generate a syntactic structure, and then generate the surface form. We show that decomposing the generation process this way leads to state-of-the-art single model performance generating from AMR without additional unlabelled data. We also demonstrate that we can generate meaning-preserving syntactic paraphrases of the same AMR graph, as judged by humans.
Keywords
Cite
@article{arxiv.1804.07707,
title = {Factorising AMR generation through syntax},
author = {Kris Cao and Stephen Clark},
journal= {arXiv preprint arXiv:1804.07707},
year = {2019}
}
Comments
Camera ready; accepted at NAACL-HLT 2019