Text-to-Text Transfer Transformer

Year: 2,020
Journal: Journal of Machine Learning Research
Languages: English, French, German, Romanian
Programming languages: Python
Input data:

Plain text

Output data:

text, words

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.

Sign In


Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.