Toward Real-Time Sentence-Level Sign Language Translation
Most sign language understanding systems operate at the level of isolated signs, limiting their usefulness in natural communication. We study sentence-level sign language translation (SLT) with the primary goal of real-time deployment rather than proposing a new translation architecture. We fine-tune a SHuBERT-ByT5 translation stack on a uniformly sampled 9,872-example subset of How2Sign, selected because of compute and storage constraints, using QLoRA while keeping SHuBERT frozen. The model obtains a validation BLEU of 16.7 and, on the test split, BLEU 15.9 and BLEURT 44.7. The main contribut
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 73%BelalC/sign2text →
- PossiblePossibly related (embedding) · 53%Fluid, natural voice translation with Gemini 3.5 Live Translate →
- PossiblePossibly related (embedding) · 51%sgl-project/sglang →
- LinkedLinked via arxiv author · 85%Thanh-Hoang Nguyen Doan →
“Toward Real-Time Sentence-Level Sign Language Translation”