A character-level transformer trained on isolated words, with a five-language label head, yields compact embeddings that rival or beat much larger pre-trained models on morphological tagging across Arabic, English, and French.
Title resolution pending
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
-
chDzDT: Word-level morphology-aware language model for Algerian social media text
A character-level transformer trained on isolated words, with a five-language label head, yields compact embeddings that rival or beat much larger pre-trained models on morphological tagging across Arabic, English, and French.