Research map / Architectures and efficiency / RNNs and normalization
MLSLT: Towards Multilingual Sign Language Translation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use dynamic routing with InterLSR and IntraLSR instead of the multilingual baseline | MSLT on SP-10, sign languages to English · SP-10 test | BLEU4: 2.12 -> 4.66 | Helped |
| Use dynamic routing with InterLSR and IntraLSR instead of separate bilingual models | MSLT on SP-10, sign languages to English · SP-10 test | ROUGE: 30.86 -> 32.70 | Helped |
| Use MLSLT rather than separate bilingual models | BFI to spoken languages on SP-10 · SP-10 test | BLEU4: 1.75 -> 2.55 | Helped |
| Use MLSLT rather than separate bilingual models | BFI to spoken languages on SP-10 · SP-10 test | ROUGE: 29.69 -> 31.47 | Helped |
| Use MLSLT rather than separate bilingual models for 10×10 language pairs | Many-to-many translation on SP-10 · SP-10, 10×10 language pairs | BLEU4: 1.66 -> 1.88 | Helped |
| Use MLSLT rather than separate bilingual models for 10×10 language pairs | Many-to-many translation on SP-10 · SP-10, 10×10 language pairs | ROUGE: 29.27 -> 30.26 | Helped |
| Translate without supervised examples for the evaluated sign-language-to-English pair | Zero-shot MLSLT · SP-10 zero-shot sign languages to English | BLEU4: 3.47 -> 2.69; 3.60 -> 3.44; 3.83 -> 3.29; 3.83 -> 3.14; 2.94 -> 2.65; 2.99 -> 2.40; 2.46 -> 1.03; 4.32 -> 1.78; 3.23 -> | Mixed |
| Add IntraLSR (ablation) | Native SLT on SP-10 · SP-10 | BLEU4: 2.27 -> 5.19 | Helped |
| Add IntraLSR (ablation) | Native SLT on SP-10 · SP-10 | ROUGE: 29.80 -> 33.33 | Helped |
| Add InterLSR (ablation) | Native SLT on SP-10 · SP-10 | BLEU4: 2.27 -> 3.58 | Helped |
| Add InterLSR (ablation) | Native SLT on SP-10 · SP-10 | ROUGE: 29.80 -> 32.20 | Helped |
| Add both IntraLSR and InterLSR (ablation) | Native SLT on SP-10 · SP-10 | BLEU4: 2.27 -> 6.30 | Helped |
Closest papers by meaning
- Scaling Sign Language Translation (NeurIPS 2024 · similarity 0.91)
- LLMs are Good Sign Language Translators (CVPR 2024 · similarity 0.89)
- YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus (ICLR 2025 · similarity 0.88)
- Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation (ICLR 2024 · similarity 0.88)
- Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues (CVPR 2025 · similarity 0.88)
- KD-MSLRT: Lightweight Sign Language Recognition Model Based on Mediapipe and 3D to 1D Knowledge Distillation (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
