# Multilingual AMR-to-Text Generation

arXiv: https://arxiv.org/abs/2011.05443 · HTML: https://mlsanity.com/paper/2011.05443/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2020.

## Built on by (most cited first, 12 of 12)

- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Translate, then Parse! A strong baseline for Cross-Lingual AMR Parsing](https://mlsanity.com/paper/2106.04565/) (2021)
- [MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages](https://mlsanity.com/paper/2208.13078/) (2022)
- [NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures](https://mlsanity.com/paper/2204.13692/) (2022)
- [T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation](https://mlsanity.com/paper/2212.01667/) (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)
- [Survey of Abstract Meaning Representation: Then, Now, Future](https://mlsanity.com/paper/2505.03229/) (2025)
- [Generalising Multilingual Concept-to-Text NLG with Language Agnostic Delexicalisation](https://mlsanity.com/paper/2105.03432/) (2021)
- [A Survey : Neural Networks for AMR-to-Text](https://mlsanity.com/paper/2206.07328/) (2022)
- [Template-based Recruitment Email Generation For Job Recommendation](https://mlsanity.com/paper/2212.02885/) (2022)
- [Evaluation of Finetuned LLMs in AMR Parsing](https://mlsanity.com/paper/2508.05028/) (2025)

## Abstract (arXiv)

Generating text from structured data is challenging because it requires bridging the gap between (i) structure and natural language (NL) and (ii) semantically underspecified input and fully specified NL output. Multilingual generation brings in an additional challenge: that of generating into languages with varied word order and morphological properties. In this work, we focus on Abstract Meaning Representations (AMRs) as structured input, where previous research has overwhelmingly focused on generating only into English. We leverage advances in cross-lingual embeddings, pretraining, and multilingual models to create multilingual AMR-to-text models that generate in twenty one different languages. For eighteen languages, based on automatic metrics, our multilingual models surpass baselines that generate into a single language. We analyse the ability of our multilingual models to accurately capture morphology and word order using human evaluation, and find that native speakers judge our generations to be fluent.