# SONAR-SLT: Multilingual Sign Language Translation via Language-Agnostic Sentence Embedding Supervision

arXiv: https://arxiv.org/abs/2510.19398 · HTML: https://mlsanity.com/paper/2510.19398/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Improving Sign Language Translation with Monolingual Data by Sign Back-Translation](https://mlsanity.com/paper/2105.12397/) (2021)
- [SONAR: Sentence-Level Multimodal and Language-Agnostic Representations](https://mlsanity.com/paper/2308.11466/) (2023)
- [Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining](https://mlsanity.com/paper/2307.14768/) (2023)
- [LLMs are Good Sign Language Translators](https://mlsanity.com/paper/2404.00925/) (2024)
- [YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus](https://mlsanity.com/paper/2306.15162/) (2023)
- [Uni-Sign: Toward Unified Sign Language Understanding at Scale](https://mlsanity.com/paper/2501.15187/) (2025)
- [Towards Privacy-Aware Sign Language Translation at Scale](https://mlsanity.com/paper/2402.09611/) (2024)
- [Considerations for meaningful sign language machine translation based on glosses](https://mlsanity.com/paper/2211.15464/) (2022)
- [SHuBERT: Self-Supervised Sign Language Representation Learning via Multi-Stream Cluster Prediction](https://mlsanity.com/paper/2411.16765/) (2024)
- [SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale](https://mlsanity.com/paper/2406.06907/) (2024)
- [JWSign: A Highly Multilingual Corpus of Bible Translations for more Diversity in Sign Language Processing](https://mlsanity.com/paper/2311.10174/) (2023)
- [Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation Model](https://mlsanity.com/paper/2505.24355/) (2025)

## Built on by (most cited first, 3 of 3)

- [Semantic Communities and Boundary-Spanning Lyrics in K-pop: A Graph-Based Unsupervised Analysis](https://mlsanity.com/paper/2602.12881/) (2026)
- [A Critical Study of Automatic Evaluation in Sign Language Translation](https://mlsanity.com/paper/2510.25434/) (2025)
- [FEA-SLT: A Gloss-Free End-to-End Framework for Facial-Expression-Aware Sign Language Translation](https://mlsanity.com/paper/2601.03549/) (2026)

## Abstract (arXiv)

Sign language translation (SLT) is typically trained with text in a single spoken language, which limits scalability and cross-language generalization. Earlier approaches have replaced gloss supervision with text-based sentence embeddings, but up to now, these remain tied to a specific language and modality. In contrast, here we employ language-agnostic, multimodal embeddings trained on text and speech from multiple languages to supervise SLT, enabling direct multilingual translation. To address data scarcity, we propose a coupled augmentation method that combines multilingual target augmentations (i.e. translations into many languages) with video-level perturbations, improving model robustness. Experiments show consistent BLEURT gains over text-only sentence embedding supervision, with larger improvements in low-resource settings. Our results demonstrate that language-agnostic embedding supervision, combined with coupled augmentation, provides a scalable and semantically robust alternative to traditional SLT training.