AdaBPE adapts BPE merge thresholds for mixed language and LaTeX
On five LaTeX and natural-language datasets, the method improves encoding and domain-specific model performance without hurting general language.
1 stories, newest first · one card per story
On five LaTeX and natural-language datasets, the method improves encoding and domain-specific model performance without hurting general language.
Today 1.6K readers · 2.5K views · 778 reads · all time 189K views