Semantic Scholar Open Access 2019 25109 sitasi

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang +4 lainnya

Abstrak

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 every language problem into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled datasets, 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 dataset, pre-trained models, and code.

Penulis (9)

C

Colin Raffel

N

Noam Shazeer

A

Adam Roberts

K

Katherine Lee

S

Sharan Narang

M

Michael Matena

Y

Yanqi Zhou

W

Wei Li

P

Peter J. Liu

Format Sitasi

Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M. et al. (2019). Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. https://www.semanticscholar.org/paper/6c4b76232bb72897685d19b3d264c6ee3005bc2b

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2019
Bahasa
en
Total Sitasi
25109×
Sumber Database
Semantic Scholar
Akses
Open Access ✓