Merging task vectors from separately fine-tuned OCR experts improves out-of-domain generalization and transfer to low-resource alphabets compared to centralized fine-tuning on the same data.
https://cl.lingfil.uu.se/~bea/borg/ (Jan 2018)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing
Merging task vectors from separately fine-tuned OCR experts improves out-of-domain generalization and transfer to low-resource alphabets compared to centralized fine-tuning on the same data.