# Select and Reorder: A Novel Approach for Neural Sign Language Production

arXiv: https://arxiv.org/abs/2404.11532 · HTML: https://mlsanity.com/paper/2404.11532/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 63 references that are in the map.
- First posted on arXiv 17 Apr 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [Transfer Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1604.02201/) (2016)
- [SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings](https://mlsanity.com/paper/2004.08728/) (2020)
- [German's Next Language Model](https://mlsanity.com/paper/2010.10906/) (2020)
- [Progressive Transformers for End-to-End Sign Language Production](https://mlsanity.com/paper/2004.14874/) (2020)
- [Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information](https://mlsanity.com/paper/2010.03142/) (2020)
- [Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production](https://mlsanity.com/paper/2203.15354/) (2022)
- [Adversarial Training for Multi-Channel Sign Language Production](https://mlsanity.com/paper/2008.12405/) (2020)
- [Joey NMT: A Minimalist NMT Toolkit for Novices](https://mlsanity.com/paper/1907.12484/) (2019)
- [Everybody Sign Now: Translating Spoken Language to Photo Realistic Sign Language Video](https://mlsanity.com/paper/2011.09846/) (2020)
- [Data Augmentation for Sign Language Gloss Translation](https://mlsanity.com/paper/2105.07476/) (2021)
- [Sign Language Production: A Review](https://mlsanity.com/paper/2103.15910/) (2021)
- [Machine Translation between Spoken Languages and Signed Languages Represented in SignWriting](https://mlsanity.com/paper/2210.05404/) (2022)
- [Changing the Representation: Examining Language Representation for Neural Sign Language Production](https://mlsanity.com/paper/2210.06312/) (2022)
- [Transcribing Natural Languages for The Deaf via Neural Editing Programs](https://mlsanity.com/paper/2112.09600/) (2021)

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

- [SignSplat: Rendering Sign Language via Gaussian Splatting](https://mlsanity.com/paper/2505.02108/) (2025)
- [SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Work](https://mlsanity.com/paper/2508.06951/) (2025)
- [From Sign Language Generation to Humanoid Execution: Vision-Language Guided Retargeting with Collision Mitigation](https://mlsanity.com/paper/2607.17769/) (2026)

## Abstract (arXiv)

Sign languages, often categorised as low-resource languages, face significant challenges in achieving accurate translation due to the scarcity of parallel annotated datasets. This paper introduces Select and Reorder (S&R), a novel approach that addresses data scarcity by breaking down the translation process into two distinct steps: Gloss Selection (GS) and Gloss Reordering (GR). Our method leverages large spoken language models and the substantial lexical overlap between source spoken languages and target sign languages to establish an initial alignment. Both steps make use of Non-AutoRegressive (NAR) decoding for reduced computation and faster inference speeds. Through this disentanglement of tasks, we achieve state-of-the-art BLEU and Rouge scores on the Meine DGS Annotated (mDGS) dataset, demonstrating a substantial BLUE-1 improvement of 37.88% in Text to Gloss (T2G) Translation. This innovative approach paves the way for more effective translation models for sign languages, even in resource-constrained settings.