Additionally trained models that accompany "Punctuation restoration improves structure understanding without supervision"
Year: 2024
Type: preprint
Abstract: Half-precision model checkpoints from our work "Punctuation restoration improves structure understanding without supervision."
Source: arXiv (Cornell University)
Institutions: Georgetown University, Korea Telecom (South Korea)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4391833684
