# AMR-to-text generation as a Traveling Salesman Problem

arXiv: https://arxiv.org/abs/1609.07451 · HTML: https://mlsanity.com/paper/1609.07451/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2016.

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

- [Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters](https://mlsanity.com/paper/2302.05900/) (2023)
- [The Generation-Recognition Asymmetry: Six Dimensions of a Fundamental Divide in Formal Language Theory](https://mlsanity.com/paper/2603.10139/) (2026)
- [A Survey : Neural Networks for AMR-to-Text](https://mlsanity.com/paper/2206.07328/) (2022)
- [Evaluation of Finetuned LLMs in AMR Parsing](https://mlsanity.com/paper/2508.05028/) (2025)

## Abstract (arXiv)

The task of AMR-to-text generation is to generate grammatical text that sustains the semantic meaning for a given AMR graph. We at- tack the task by first partitioning the AMR graph into smaller fragments, and then generating the translation for each fragment, before finally deciding the order by solving an asymmetric generalized traveling salesman problem (AGTSP). A Maximum Entropy classifier is trained to estimate the traveling costs, and a TSP solver is used to find the optimized solution. The final model reports a BLEU score of 22.44 on the SemEval-2016 Task8 dataset.