We evaluated GPT-3 and ChatGPT on two graph-to-text generation benchmarks: AGENDA and WebNLG.
We collected the text generated by GPT-3 and ChatGPT in data.
Please cite our work as follows:
@inproceedings{yuan-faerber-2023-evaluating,
title = "Evaluating Generative Models for Graph-to-Text Generation",
author = "Yuan, Shuzhou and
Faerber, Michael",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-1.133",
pages = "1256--1264",
}