| Control Prefixes for Parameter-Efficient Text Generation | ✓ Link | 67.32 | | | | | | Control Prefixes (A1, T5-large) | 2021-10-15 |
| Control Prefixes for Parameter-Efficient Text Generation | ✓ Link | 67.15 | | | | | | Control Prefixes (A1, A2, T5-large) | 2021-10-15 |
| FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation | ✓ Link | 67.08 | 48.34 | | 99.09 | | | JointGT Baseline | 2023-10-25 |
| FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation | ✓ Link | 67.04 | 48.35 | | 99.44 | | | T5B Baseline | 2023-10-25 |
| FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation | ✓ Link | 67.04 | 48.22 | | 99.71 | | | FactT5B | 2023-10-25 |
| FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation | ✓ Link | 66.89 | 48.19 | | 99.67 | | | FactJointGT | 2023-10-25 |
| Stage-wise Fine-tuning for Graph-to-Text Generation | ✓ Link | 66.07 | | | | | | T5-large + Wiki + Position | 2021-05-17 |
| HTLM: Hyper-Text Pre-Training and Prompting of Language Models | | 65.4 | | | | | | HTML (fine-tuning) | 2021-07-14 |
| Investigating Pretrained Language Models for Graph-to-Text Generation | ✓ Link | 65.05 | | | | | | T5-small | 2020-07-16 |
| TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy | | 64.73 | 45.53 | 6.2 | | | | TrICy (trK = trk* = 0.24) | 2024-01-25 |
| Text-to-Text Pre-Training for Data-to-Text Tasks | ✓ Link | 64.7 | | | | | | T5-Base | 2020-05-21 |
| TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy | | 64.08 | 45.23 | 6.2 | | | | TrICy (trK = 0) | 2024-01-25 |
| Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs | ✓ Link | 63.69 | | | | | | CGE-LW (Levi Graph) | 2020-01-29 |
| Structural Information Preserving for Graph-to-Text Generation | ✓ Link | 62.89 | | | | | | Multiview-G2S | 2021-02-12 |
| Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs | | 61.15 | | | | | | Graformer | 2020-06-16 |
| GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data | | 58.6 | | | | | | GTR-LSTM (entity masking) | 2018-07-01 |
| Neural data-to-text generation: A comparison between pipeline and end-to-end architectures | ✓ Link | 57.20 | | | | | | E2E GRU | 2019-08-23 |
| Deep Graph Convolutional Encoders for Structured Data to Text Generation | ✓ Link | 55.9 | | | | | | GCN EC | 2018-10-23 |
| Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation | ✓ Link | 47.4 | | | | | | BestPlan | 2019-04-06 |
| TextBox 2.0: A Text Generation Library with Pre-trained Language Models | ✓ Link | | 47.78 | | | 67.33 | 76.83 | BART (TextBox 2.0) | 2022-12-26 |