# Modeling Intensification for Sign Language Generation: A Computational Approach

arXiv: https://arxiv.org/abs/2203.09679 · HTML: https://mlsanity.com/paper/2203.09679/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 50 references that are in the map.
- First posted on arXiv 18 Mar 2022.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation](https://mlsanity.com/paper/2003.13830/) (2020)
- [How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language](https://mlsanity.com/paper/2008.08143/) (2020)
- [Progressive Transformers for End-to-End Sign Language Production](https://mlsanity.com/paper/2004.14874/) (2020)
- [Including Signed Languages in Natural Language Processing](https://mlsanity.com/paper/2105.05222/) (2021)
- [Adversarial Training for Multi-Channel Sign Language Production](https://mlsanity.com/paper/2008.12405/) (2020)
- [Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives](https://mlsanity.com/paper/2107.11317/) (2021)
- [Data Augmentation for Sign Language Gloss Translation](https://mlsanity.com/paper/2105.07476/) (2021)
- [Including Facial Expressions in Contextual Embeddings for Sign Language Generation](https://mlsanity.com/paper/2202.05383/) (2022)
- [On Robustness and Bias Analysis of BERT-based Relation Extraction](https://mlsanity.com/paper/2009.06206/) (2020)

## Built on by (most cited first, 9 of 9)

- [T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text](https://mlsanity.com/paper/2406.07119/) (2024)
- [An Active Learning Framework for Inclusive Generation by Large Language Models](https://mlsanity.com/paper/2410.13641/) (2024)
- [Unsupervised Sign Language Translation and Generation](https://mlsanity.com/paper/2402.07726/) (2024)
- [SiLVERScore: Semantically-Aware Embeddings for Sign Language Generation Evaluation](https://mlsanity.com/paper/2509.03791/) (2025)
- [A Survey on Deep Multi-modal Learning for Body Language Recognition and Generation](https://mlsanity.com/paper/2308.08849/) (2023)
- [Generating Signed Language Instructions in Large-Scale Dialogue Systems](https://mlsanity.com/paper/2410.14026/) (2024)
- [Dialogue with Robots: Proposals for Broadening Participation and Research in the SLIVAR Community](https://mlsanity.com/paper/2404.01158/) (2024)
- [Targeted Linguistic Analysis of Sign Language Models with Minimal Translation Pairs](https://mlsanity.com/paper/2604.27232/) (2026)
- [DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation](https://mlsanity.com/paper/2609.02796/) (2026)

## Abstract (arXiv)

End-to-end sign language generation models do not accurately represent the prosody in sign language. A lack of temporal and spatial variations leads to poor-quality generated presentations that confuse human interpreters. In this paper, we aim to improve the prosody in generated sign languages by modeling intensification in a data-driven manner. We present different strategies grounded in linguistics of sign language that inform how intensity modifiers can be represented in gloss annotations. To employ our strategies, we first annotate a subset of the benchmark PHOENIX-14T, a German Sign Language dataset, with different levels of intensification. We then use a supervised intensity tagger to extend the annotated dataset and obtain labels for the remaining portion of it. This enhanced dataset is then used to train state-of-the-art transformer models for sign language generation. We find that our efforts in intensification modeling yield better results when evaluated with automatic metrics. Human evaluation also indicates a higher preference of the videos generated using our model.