technique
Connectionist Temporal Classification
techniqueactiveprovisional
connectionist-temporal-classification-a611a712·1 events·first seen 24h agoAliases: Connectionist Temporal Classification
Co-occurring entities
More like this (12)
Neural Classification TreesTemporal Difference Learningtemporally ordered pre-trainingLabel Context Classifiertemporal knowledge graphshapelet-based time-series classificationtemporal visual event understandingUEA Time Series Classification RepositoryA Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian NoiseFlashbackCL: Mitigating Temporal Forgetting in Federated LearningTemporal SimultaneityMulti-Task Bayesian In-Context Learning
Recent events (1)
CANDLE: Lightweight CTC-based Arabic character deduplication for social media text normalization
CANDLE is a lightweight Arabic text normalization system that uses Connectionist Temporal Classification (CTC) to deduplicate informal character elongation without handcrafted rules or morphological analyzers. Evaluated on three benchmarks including social media text, the CTC model achieves 5.37% Sentence Error Rate and is distilled from 6 layers to 2 with minimal performance loss. A key downstream benefit is up to 12.8% reduction in tokenizer fertility across Arabic LLM tokenizers, lowering inference costs and improving context window utilization. Code and models are publicly released.