On a new 144,000-word annotated dataset for Wolayta and Gofa, BERT-base-uncased embeddings with an LSTM classifier reach 0.72 F1, the best of seven compared approaches.
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
-
Bilingual Word Level Language Identification for Omotic Languages
On a new 144,000-word annotated dataset for Wolayta and Gofa, BERT-base-uncased embeddings with an LSTM classifier reach 0.72 F1, the best of seven compared approaches.