Homophone normalization in Amharic training data can harm cross-lingual machine translation to Tigrinya and Ge'ez, but applying the normalization only at scoring time recovers BLEU gains.
https://library.bu.edu/amharic/Home Research: Language Learning - Amharic : Home
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script
Homophone normalization in Amharic training data can harm cross-lingual machine translation to Tigrinya and Ge'ez, but applying the normalization only at scoring time recovers BLEU gains.