Haoran Xu
Haoran Xu
Home
Experience
Preprints
Publications
Contact
Light
Dark
Automatic
Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
Tianjian Li
,
Haoran Xu
,
Philipp Koehn
,
Daniel Khashabi
,
Kenton Murray
September 2023
PDF
Code
Type
Conference paper
Publication
ICLR 2024
(Spotlight)
Related
Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets
Efficiently Harnessing Parameter Importance for Better Training
Cite
×