# Enhancing AMR-to-Text Generation with Dual Graph Representations

arXiv: https://arxiv.org/abs/1909.00352 · HTML: https://mlsanity.com/paper/1909.00352/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2019.

## Built on by (most cited first, 24 of 24)

- [Structural Adapters in Pretrained Language Models for AMR-to-text Generation](https://mlsanity.com/paper/2103.09120/) (2021)
- [FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations](https://mlsanity.com/paper/2204.06508/) (2022)
- [Structural Information Preserving for Graph-to-Text Generation](https://mlsanity.com/paper/2102.06749/) (2021)
- [Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs](https://mlsanity.com/paper/2307.07312/) (2023)
- [Logic-Consistency Text Generation from Semantic Parses](https://mlsanity.com/paper/2108.00577/) (2021)
- [Evaluating Generative Models for Graph-to-Text Generation](https://mlsanity.com/paper/2307.14712/) (2023)
- [Stage-wise Fine-tuning for Graph-to-Text Generation](https://mlsanity.com/paper/2105.08021/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)](https://mlsanity.com/paper/2406.14541/) (2024)
- [Better Smatch = Better Parser? AMR evaluation is not so simple anymore](https://mlsanity.com/paper/2210.06461/) (2022)
- [Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables](https://mlsanity.com/paper/2309.11049/) (2023)
- [Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation](https://mlsanity.com/paper/2210.09773/) (2022)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation](https://mlsanity.com/paper/2109.03808/) (2021)
- [Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation](https://mlsanity.com/paper/2212.01956/) (2022)
- [How to Train Your Agent to Read and Write](https://mlsanity.com/paper/2101.00916/) (2021)
- [Levi Graph AMR Parser using Heterogeneous Attention](https://mlsanity.com/paper/2107.04152/) (2021)
- [Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters](https://mlsanity.com/paper/2302.05900/) (2023)
- [Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning](https://mlsanity.com/paper/2308.05317/) (2023)
- [GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism](https://mlsanity.com/paper/2404.06911/) (2024)
- [Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models](https://mlsanity.com/paper/2309.12294/) (2023)
- [Graph Neural Networks for Natural Language Processing: A Survey](https://mlsanity.com/paper/2106.06090/) (2021)
- [A Survey : Neural Networks for AMR-to-Text](https://mlsanity.com/paper/2206.07328/) (2022)
- [Controlling Topic-Focus Articulation in Meaning-to-Text Generation using Graph Neural Networks](https://mlsanity.com/paper/2310.02053/) (2023)

## Abstract (arXiv)

Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure of a graph with labeled edges. To address this difficulty, we propose a novel graph-to-sequence model that encodes different but complementary perspectives of the structural information contained in the AMR graph. The model learns parallel top-down and bottom-up representations of nodes capturing contrasting views of the graph. We also investigate the use of different node message passing strategies, employing different state-of-the-art graph encoders to compute node representations based on incoming and outgoing perspectives. In our experiments, we demonstrate that the dual graph representation leads to improvements in AMR-to-text generation, achieving state-of-the-art results on two AMR datasets.