ASL-MTP, the first minimal-pair benchmark for sign-language translation models, shows the state-of-the-art SHuBERT+ByT5 reaches above-chance accuracy on most phenomena but depends on hand cues and largely misses non-manual facial/body cues.
Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Targeted Linguistic Analysis of Sign Language Models with Minimal Translation Pairs
ASL-MTP, the first minimal-pair benchmark for sign-language translation models, shows the state-of-the-art SHuBERT+ByT5 reaches above-chance accuracy on most phenomena but depends on hand cues and largely misses non-manual facial/body cues.