SiLVERScore: Semantically-Aware Embeddings for Sign Language Generation Evaluation
Imai, Saki, İnan, Mert, Sicilia, Anthony, Alikhani, Malihe
–arXiv.org Artificial Intelligence
Evaluating sign language generation is often done through back-translation, where generated signs are first recognized back to text and then compared to a reference using text-based metrics. However, this two-step evaluation pipeline introduces ambiguity: it not only fails to capture the multimodal nature of sign language-such as facial expressions, spatial grammar, and prosody-but also makes it hard to pinpoint whether evaluation errors come from sign generation model or the translation system used to assess it. In this work, we propose SiLVERScore, a novel semantically-aware embedding-based evaluation metric that assesses sign language generation in a joint embedding space. Our contributions include: (1) identifying limitations of existing metrics, (2) introducing SiLVERScore for semantically-aware evaluation, (3) demonstrating its robustness to semantic and prosodic variations, and (4) exploring generalization challenges across datasets. On PHOENIX-14T and CSL-Daily datasets, SiLVERScore achieves near-perfect discrimination between correct and random pairs (ROC AUC = 0.99, overlap < 7%), substantially outperforming traditional metrics.
arXiv.org Artificial Intelligence
Sep-5-2025
- Country:
- Europe (1.00)
- North America > United States (0.46)
- Genre:
- Research Report > New Finding (0.68)
- Industry:
- Education > Curriculum > Subject-Specific Education (1.00)
- Technology: