Non-contextual (first-layer) BERT embeddings generally outperform FastText on six Marathi classification tasks, though they lose on sentiment and long-document news.
Organization of Knowledge and Advanced Technologies
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Non-Contextual BERT or FastText? A Comparative Analysis
Non-contextual (first-layer) BERT embeddings generally outperform FastText on six Marathi classification tasks, though they lose on sentiment and long-document news.