Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
This work addresses the diversity and complexity of transfer learning methods in NLP, providing a comprehensive study and resources for future research.
The paper introduces a unified text-to-text framework to systematically explore transfer learning techniques in NLP, achieving state-of-the-art results on multiple benchmarks such as summarization and question answering.
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new ``Colossal Clean Crawled Corpus'', we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.