Semantic smoothing formulates next-word distribution estimation under KL loss with embedding-based KL-proximity side information, yielding an interpolation estimator with worst-case risk O(min{Δ, d/n}) that empirically reduces perplexity on bigram models.
The Mixture Approach To Universal Model Selection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.IT 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Semantic Smoothing for Language Models via Distribution Estimation and Embeddings
Semantic smoothing formulates next-word distribution estimation under KL loss with embedding-based KL-proximity side information, yielding an interpolation estimator with worst-case risk O(min{Δ, d/n}) that empirically reduces perplexity on bigram models.