# Factorising AMR generation through syntax

arXiv: https://arxiv.org/abs/1804.07707 · HTML: https://mlsanity.com/paper/1804.07707/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2018.

## Built on by (most cited first, 4 of 4)

- [Structural Information Preserving for Graph-to-Text Generation](https://mlsanity.com/paper/2102.06749/) (2021)
- [ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation](https://mlsanity.com/paper/2305.16585/) (2023)
- [Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters](https://mlsanity.com/paper/2302.05900/) (2023)
- [A Survey : Neural Networks for AMR-to-Text](https://mlsanity.com/paper/2206.07328/) (2022)

## Abstract (arXiv)

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.