MTG: A Benchmark Suite for Multilingual Text Generation
Yiran Chen, Zhenqiao Song, Xianze Wu, Danqing Wang, Jingjing Xu, Jiaze Chen, Hao Zhou, Lei Li
Abstract
We introduce MTG, a new benchmark suite for training and evaluating multilingual text generation. 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). The multiway setup enables testing knowledge transfer capabilities for a model across languages and tasks. Using MTG, we train and analyze several popular multilingual generation models from different aspects. Our benchmark suite fosters model performance enhancement with more human-annotated parallel data. It provides comprehensive evaluations with diverse generation scenarios. Code and data are available at https://github.com/zide05/MTG.- Anthology ID:
- 2022.findings-naacl.192
- Volume:
- Findings of the Association for Computational Linguistics: NAACL 2022
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2508–2527
- Language:
- URL:
- https://aclanthology.org/2022.findings-naacl.192
- DOI:
- 10.18653/v1/2022.findings-naacl.192
- Cite (ACL):
- Yiran Chen, Zhenqiao Song, Xianze Wu, Danqing Wang, Jingjing Xu, Jiaze Chen, Hao Zhou, and Lei Li. 2022. MTG: A Benchmark Suite for Multilingual Text Generation. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2508–2527, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- MTG: A Benchmark Suite for Multilingual Text Generation (Chen et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-naacl.192.pdf
- Code
- zide05/mtg
- Data
- CNN/Daily Mail, GEM, ROCStories, SQuAD