MTG: A Benchmark Suite for Multilingual Text Generation

doi:doi:10.57702/rnp41kvi

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).

BibTex:

@dataset{Yiran_Chen_and_Zhenqiao_Song_and_Xianze_Wu_and_Danqing_Wang_and_Jingjing_Xu_and_Jiaze_Chen_and_Hao_Zhou_and_Lei_Li_2024,
    abstract = {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).},
    author = {Yiran Chen and Zhenqiao Song and Xianze Wu and Danqing Wang and Jingjing Xu and Jiaze Chen and Hao Zhou and Lei Li},
    doi = {10.57702/rnp41kvi},
    institution = {No Organization},
    keyword = {'Benchmark', 'Benchmark Suite', 'Multilingual', 'Text Generation'},
    month = {dec},
    publisher = {TIB},
    title = {MTG: A Benchmark Suite for Multilingual Text Generation},
    url = {https://service.tib.eu/ldmservice/dataset/mtg--a-benchmark-suite-for-multilingual-text-generation},
    year = {2024}
}