A lexical-knowledge projection of BERT word embeddings, trained with center loss, improves small-data text classification accuracy across six datasets.
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
-
Domain Lexical Knowledge-based Word Embedding Learning for Text Classification under Small Data
A lexical-knowledge projection of BERT word embeddings, trained with center loss, improves small-data text classification accuracy across six datasets.