MVP: Multi-task Supervised Pre-training for Natural Language Generation
Tang, Tianyi, Li, Junyi, Zhao, Wayne Xin, Wen, Ji-Rong
–arXiv.org Artificial Intelligence
Pre-trained language models (PLMs) have achieved remarkable success in natural language generation (NLG) tasks. Up to now, most NLG-oriented PLMs are pre-trained in an unsupervised manner using the large-scale general corpus. In the meanwhile, an increasing number of models pre-trained with labeled data (i.e. "supervised pre-training") showcase superior performance compared to unsupervised pre-trained models. Motivated by the success of supervised pre-training, we propose Multi-task superVised Pre-training (MVP) for natural language generation. We collect a large-scale natural language generation corpus, MVPCorpus, from $77$ datasets over $11$ diverse NLG tasks. Then we unify these examples into a general text-to-text format to pre-train the text generation model MVP in a supervised manner. For each task, we further pre-train specific soft prompts to stimulate the model's capacity to perform a specific task. Our MVP model can be seen as a practice that utilizes recent instruction tuning on relatively small PLMs. Extensive experiments have demonstrated the effectiveness and generality of our MVP model in a number of NLG tasks, which achieves state-of-the-art performance on $13$ out of $17$ datasets, outperforming BART by $9.3\%$ and Flan-T5 by $5.8\%$.
arXiv.org Artificial Intelligence
May-28-2023
- Country:
- Asia > Middle East
- Europe (1.00)
- North America > United States (1.00)
- Genre:
- Research Report > New Finding (0.87)
- Industry:
- Consumer Products & Services (0.68)
- Education (0.67)
- Government > Regional Government
- Asia Government > Middle East Government (0.46)
- Health & Medicine > Therapeutic Area
- Psychiatry/Psychology (0.45)
- Law (1.00)
- Transportation
- Technology: