mlsanityData to 14 Oct 2026

Stage-wise Fine-tuning for Graph-to-Text Generation

arXiv 2105.08021 ↗First posted 17 May 2021cs.CL cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes the model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 17 May 2021.

Builds on

26 of 41 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  6. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  7. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  8. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 428
  9. 2017Challenges in Data-to-Document Generationcited by 226
  10. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 145
  11. 2019Text Generation from Knowledge Graphs with Graph Transformerscited by 122
  12. 2019Handling Divergent Reference Texts when Evaluating Table-to-Text Generationcited by 119
14 more
  1. 2020Investigating Pretrained Language Models for Graph-to-Text Generationcited by 117
  2. 2018Data-to-Text Generation with Content Selection and Planningcited by 106
  3. 2020Text-to-Text Pre-Training for Data-to-Text Taskscited by 104
  4. 2019Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generationcited by 75
  5. 2018A Graph-to-Sequence Model for AMR-to-Text Generationcited by 56
  6. 2019Neural data-to-text generation: A comparison between pipeline and end-to-end architecturescited by 51
  7. 2020Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraintscited by 48
  8. 2020Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelitycited by 35
  9. 2020Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphscited by 30
  10. 2018Deep Graph Convolutional Encoders for Structured Data to Text Generationcited by 27
  11. 2020Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondencecited by 25
  12. 2019Enhancing AMR-to-Text Generation with Dual Graph Representationscited by 24
  13. 2018Describing a Knowledge Basecited by 18
  14. 2019Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time)cited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 2; 2024: 4; 2025: 1; 2026: 1.

11 papers.

  1. 2022Self-supervised Graph Masking Pre-training for Graph-to-Text Generationcited by 8
  2. 2024The Effects of Hallucinations in Synthetic Training Data for Relation Extractioncited by 7
  3. 2024A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generationcited by 6
  4. 2023EEL: Efficiently Encoding Lattices for Rerankingcited by 4
  5. 2026ADEPT: Adaptive Dynamic Early-Exit Process for Transformerscited by 4
  6. 2021Triples-to-Text Generation with Reinforcement Learning Based Graph-augmented Neural Networkscited by 1
  7. 2022XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languagescited by 1
  8. 2023Knowledge Graph for NLG in the context of conversational agentscited by 1
  9. 2024TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copycited by 0
  10. 2024Enterprise Use Cases Combining Knowledge Graphs and Natural Language Processingcited by 0
  11. 2025Ta-G-T: Subjectivity Capture in Table to Text Generation via RDF Graphscited by 0