Cite
Notes
Only stored in your browser.
Attribution
MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
arXiv 2023
Corrected CBOW Performs as well as Skip-gram
corrected-cbow-performs-as-well-as-skip-gram
from 2 papers
Adrian Benton
David Rosenberg
Karl Stratos
Mark Dredze
Mohit Bansal
Shijie Wu
Shiyue Zhang
Steven Lu