Other
Transformers
Safetensors
English
t5
text2text-generation
text-to-graph
webnlg
regen
text-generation-inference
Instructions to use Loria-MosAIk/regen-webnlg-t2g-ce with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Loria-MosAIk/regen-webnlg-t2g-ce with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Loria-MosAIk/regen-webnlg-t2g-ce") model = AutoModelForSeq2SeqLM.from_pretrained("Loria-MosAIk/regen-webnlg-t2g-ce", device_map="auto") - Notebooks
- Google Colab
- Kaggle
List the original paper and XQDT BibTeX entries on the model card
Browse files
README.md
CHANGED
|
@@ -42,4 +42,50 @@ The [base T5-large model](https://huggingface.co/google-t5/t5-large) is distribu
|
|
| 42 |
|
| 43 |
## Citation
|
| 44 |
|
| 45 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
## Citation
|
| 44 |
|
| 45 |
+
Original ReGen model: [Dognin et al. (2021)](https://arxiv.org/abs/2108.12472).
|
| 46 |
+
|
| 47 |
+
```bibtex
|
| 48 |
+
@inproceedings{dognin-etal-2021-regen,
|
| 49 |
+
title = "{R}e{G}en: {R}einforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models",
|
| 50 |
+
author = "Dognin, Pierre and
|
| 51 |
+
Padhi, Inkit and
|
| 52 |
+
Melnyk, Igor and
|
| 53 |
+
Das, Payel",
|
| 54 |
+
editor = "Moens, Marie-Francine and
|
| 55 |
+
Huang, Xuanjing and
|
| 56 |
+
Specia, Lucia and
|
| 57 |
+
Yih, Scott Wen-tau",
|
| 58 |
+
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
|
| 59 |
+
month = nov,
|
| 60 |
+
year = "2021",
|
| 61 |
+
address = "Online and Punta Cana, Dominican Republic",
|
| 62 |
+
publisher = "Association for Computational Linguistics",
|
| 63 |
+
url = "https://aclanthology.org/2021.emnlp-main.83/",
|
| 64 |
+
doi = "10.18653/v1/2021.emnlp-main.83",
|
| 65 |
+
pages = "1084--1099"
|
| 66 |
+
}
|
| 67 |
+
```
|
| 68 |
+
|
| 69 |
+
This checkpoint and reproduction code: [Efimov-Zhang et al. (2026)](https://aclanthology.org/2026.emnlp-main.397/).
|
| 70 |
+
|
| 71 |
+
```bibtex
|
| 72 |
+
@inproceedings{efimov-zhang-etal-2026-xqdt,
|
| 73 |
+
title = "{XQDT}: e{X}plainable and Quantitative Data-Text Alignment Metric with Feedback Signals",
|
| 74 |
+
author = "Efimov-Zhang, Kun and
|
| 75 |
+
Song, Yifei and
|
| 76 |
+
Gardent, Claire",
|
| 77 |
+
editor = "Lee, Hung-Yi and
|
| 78 |
+
Dev, Sunipa and
|
| 79 |
+
Li, Jessy and
|
| 80 |
+
Elliott, Desmond",
|
| 81 |
+
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
|
| 82 |
+
month = oct,
|
| 83 |
+
year = "2026",
|
| 84 |
+
address = "Budapest, Hungary",
|
| 85 |
+
publisher = "Association for Computational Linguistics",
|
| 86 |
+
url = "https://aclanthology.org/2026.emnlp-main.397/",
|
| 87 |
+
doi = "10.18653/2026.emnlp-main.397",
|
| 88 |
+
pages = "9121--9157",
|
| 89 |
+
ISBN = "979-8-89176-459-0"
|
| 90 |
+
}
|
| 91 |
+
```
|