MTG: A Benchmark Suite for Multilingual Text Generation
This provides a new benchmark for researchers in multilingual NLP, but it is incremental as it builds on existing multilingual and text generation work.
The authors introduced MTG, a benchmark suite for multilingual text generation, tackling the need for comprehensive evaluation across languages and tasks, and reported it as the largest human-annotated dataset with 400k entries.
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 \url{https://github.com/zide05/MTG}.