IT5: Text-to-text Pretraining for Italian Language Understanding and Generation
This addresses the problem of limited resources for Italian natural language processing, providing a monolingual solution that improves performance for tasks in this domain.
The authors tackled the lack of pretrained encoder-decoder models for Italian by introducing IT5, a family of models pretrained on a cleaned Italian corpus, which outperformed multilingual baselines and set a new state-of-the-art for Italian language generation.
We introduce IT5, the first family of encoder-decoder transformer models pretrained specifically on Italian. We document and perform a thorough cleaning procedure for a large Italian corpus and use it to pretrain four IT5 model sizes. We then introduce the ItaGen benchmark, which includes a broad range of natural language understanding and generation tasks for Italian, and use it to evaluate the performance of IT5 models and multilingual baselines. We find monolingual IT5 models to provide the best scale-to-performance ratio across tested models, consistently outperforming their multilingual counterparts and setting a new state-of-the-art for Italian language generation.