Transformer-XL

Year: 2,019
Journal: Association for Computational Linguistics
Languages: All Languages
Programming languages: Python
Input data:

sentences

We propose a novel neural architecture Transformer-XL that enables learning dependency beyond a fixed length without disrupting temporal coherence. It consists of a segment-level recurrence mechanism and a novel positional encoding scheme. Our method not only enables capturing longer-term dependency, but also resolves the context fragmentation problem.

Sign In

Register

Reset Password

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