mlsanityData to 7 Oct 2026

GPT-too: A language-model-first approach for AMR-to-text generation

arXiv 2005.09123 ↗First posted 18 May 2020cs.CL cs.LGcited by 38

Not on the map. Why?

Abstract (arXiv)

Meaning Representations (AMRs) are broad-coverage sentence-level semantic graphs. Existing approaches to generating text from AMR have focused on training sequence-to-sequence or graph-to-sequence models on AMR annotated data only. In this paper, we propose an alternative approach that combines a strong pre-trained language model with cycle consistency-based re-scoring. Despite the simplicity of the approach, our experimental results show these models outperform all previous techniques on the English LDC2017T10dataset, including the recent use of transformer architectures. In addition to the standard evaluation metrics, we provide human evaluation experiments that further substantiate the strength of our approach.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 12; 2023: 3; 2024: 4; 2025: 4.

38 papers.

Sort:

  1. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  2. 2021Pretrained Language Models for Text Generation: A Surveycited by 95
  3. 2021Tailor: Generating and Perturbing Text with Semantic Controlscited by 67
  4. 2021JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphscited by 58
  5. 2022Graph Pre-training for AMR Parsing and Generationcited by 55
  6. 2021Structural Adapters in Pretrained Language Models for AMR-to-text Generationcited by 48
  7. 2021Coherence boosting: When your pretrained language model is not paying enough attentioncited by 38
  8. 2021Maximum Bayes Smatch Ensemble Distillation for AMR Parsingcited by 27
  9. 2022DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulationscited by 25
  10. 2021Structural Information Preserving for Graph-to-Text Generationcited by 24
  11. 2024Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challengescited by 18
  12. 2022GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generationcited by 16
26 more
  1. 2021Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labelingcited by 11
  2. 2021Constrained Text Generation with Global Guidance -- Case Study on CommonGencited by 10
  3. 2021Graphine: A Dataset for Graph-aware Terminology Definition Generationcited by 10
  4. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  5. 2021Bootstrapping Multilingual AMR with Contextual Word Alignmentscited by 8
  6. 2022What Makes Data-to-Text Generation Hard for Pretrained Language Models?cited by 8
  7. 2022Self-supervised Graph Masking Pre-training for Graph-to-Text Generationcited by 8
  8. 2021Contextualized Scene Imagination for Generative Commonsense Reasoningcited by 7
  9. 2021LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-trainingcited by 5
  10. 2022Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representationcited by 4
  11. 2024A Systematic Review of Data-to-Text NLGcited by 4
  12. 2024Narrating Causal Graphs with Large Language Modelscited by 4
  13. 2021Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generationcited by 3
  14. 2021Document Automation Architectures and Technologies: A Surveycited by 3
  15. 2022On the Role of Pre-trained Language Models in Word Ordering: A Case Study with BARTcited by 2
  16. 2024GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanismcited by 2
  17. 2025An evaluation of LLMs and Google Translate for translation of selected Indian languages via sentiment and semantic analysescited by 2
  18. 2025Survey of Abstract Meaning Representation: Then, Now, Futurecited by 2
  19. 2022Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Modelcited by 1
  20. 2022Selective Token Generation for Few-shot Natural Language Generationcited by 1
  21. 2023Knowledge Graph for NLG in the context of conversational agentscited by 1
  22. 2023Document Automation Architectures: Updated Survey in Light of Large Language Modelscited by 1
  23. 2023Not Enough Labeled Data? Just Add Semantics: A Data-Efficient Method for Inferring Online Health Textscited by 1
  24. 2022A Survey : Neural Networks for AMR-to-Textcited by 0
  25. 2025SAFT: Structure-Aware Fine-Tuning of LLMs for AMR-to-Text Generationcited by 0
  26. 2025Evaluation of Finetuned LLMs in AMR Parsingcited by 0