SciFive: a text-to-text transformer model for biomedical literature

• DOI: 10.48550/arxiv.2106.03598
• Publication Date: 2021-01-01
• Authors: Phan, Long N.; Anibal, James T.; Tran, Hieu; Chanana, Shaurya; Bahadroglu, Erol; Peltekian, Alec; Altan-Bonnet, Gré...
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Science - Computation and Language; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Computation and Language (cs.CL); Machine Learning (cs.LG)

In this report, we introduce SciFive, a domain-specific T5 model that has been pre-trained on large biomedical corpora. Our model outperforms the current SOTA methods (i.e. BERT, BioBERT, Base T5) on tasks in named entity relation, relation extraction, natural language inference, and question-answering. We show that text-generation methods have significant potential in a broad array of biomedical NLP tasks, particularly those requiring longer, more complex outputs. Our results support the exploration of more difficult text generation tasks and the development of new methods in this area