MTG: A Benchmark Suite for Multilingual Text Generation

MTG is a multilingual multiway text generation benchmark suite. It is the first-proposed multilingual multiway text generation dataset with the largest human-annotated data (400k). It includes four generation tasks (story generation, question generation, title generation and text summarization) across five languages (English, German, French, Spanish and Chinese).

Data and Resources

Cite this as

Yiran Chen, Zhenqiao Song, Xianze Wu, Danqing Wang, Jingjing Xu, Jiaze Chen, Hao Zhou, Lei Li (2024). Dataset: MTG: A Benchmark Suite for Multilingual Text Generation. https://doi.org/10.57702/rnp41kvi

DOI retrieved: December 17, 2024

Additional Info

Field Value
Created December 17, 2024
Last update December 17, 2024
Defined In https://doi.org/10.48550/arXiv.2108.07140
Citation
  • https://doi.org/10.18653/v1/2023.emnlp-main.616
Author Yiran Chen
More Authors
Zhenqiao Song
Xianze Wu
Danqing Wang
Jingjing Xu
Jiaze Chen
Hao Zhou
Lei Li
Homepage https://github.com/zide05/MTG