vix.ing · top · new · best · stats · spec

Factorising AMR generation through syntax

2018/04/20 by Kris Cao, Stephen Clark, Cao, Kris +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1804.07707

openalex publication_date 2018/04/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

Related