Presents the first online learning-to-defer algorithm with regret bounds O((n + n_e) T^{2/3}) generally and O((n + n_e) sqrt(T)) under low noise for multiclass classification with varying experts.
LUKE : Deep Contextualized Entity Representations with Entity-aware Self-attention
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
JFinTEB is the first benchmark for evaluating Japanese financial text embeddings across retrieval and classification tasks derived from realistic financial scenarios.
citing papers explorer
-
Online Learning-to-Defer with Varying Experts
Presents the first online learning-to-defer algorithm with regret bounds O((n + n_e) T^{2/3}) generally and O((n + n_e) sqrt(T)) under low noise for multiclass classification with varying experts.
-
JFinTEB: Japanese Financial Text Embedding Benchmark
JFinTEB is the first benchmark for evaluating Japanese financial text embeddings across retrieval and classification tasks derived from realistic financial scenarios.