DiscoSign is a new computational framework that translates text into sign language glosses while explicitly handling discourse-level phenomena. It focuses on three key aspects: spatial coreference resolution to keep entities in consistent spatial positions, Question-Answer Clauses (QACs) that serve specific discourse functions, and concept-gloss consistency to maintain stable mappings between English concepts and ASL signs. The authors introduce novel evaluation metrics tailored to these discourse dimensions and demonstrate that DiscoSign improves spatial consistency and entity tracking compared to sentence-only translation models, without sacrificing single-sentence gloss quality.
By Vasileios Baltatzis, Mert Inan, Connor Gillis, Raja Kushalnagar, Lorna Quandt, Leah Findlater, Colin Lea
DiscoSign is a discourse-aware text-to-sign-language gloss translation system that builds on a modular Large Language Model framework. It tackles three key discourse phenomena: spatial coreference resolution, Question-Answer Clauses (QACs), and concept-gloss consistency. The authors introduce new evaluation metrics and demonstrate that DiscoSign improves spatial consistency and entity tracking compared to sentence-only translation while maintaining competitive single-sentence gloss quality.
SignGPT is a unified, pose‑based framework that performs gloss‑free sign language translation (SLT) and generation (SLG) by integrating part‑aware hierarchical representations of body, hand, and facial motion into a shared language model. It uses asymmetric multi‑token prediction and progressive training for bidirectional modeling, and is evaluated on How2Sign (ASL) and Phoenix‑2014T (DGS) with benchmark comparisons, qualitative analyses, and component ablations. An exploratory study with 12 Deaf ASL signers demonstrates a sign‑to‑sign response pipeline, suggesting that unified modeling can support sign language conversation (SLC).
By Ronghui Li, Jun Dong, Zhongyuan Hu, Zunnan Xu, Jun Zhou, Liyuan Chen, Shuoling Liu, Jiangpeng Yan, Jie Guo, Xiu Li, Linchao Bao
arXiv:2610.00881v1 Announce Type: new
Abstract: Sign language machine translation has progressed substantially over the past decade, evolving from isolated sign recognition to end-to-end translation...
By Ozge Mercanoglu Sincan, Anton Pelykh, Edward Fish, Harry Walsh, JianHe Low, Karahan Sahin, Oline Ranum, Sobhan Asasi, Steven Emery, Richard Bowden
The paper introduces FS23K, a large-scale British Sign Language fingerspelling dataset created through an iterative annotation framework. It also presents a recognition model that incorporates bi‑manual interactions and mouthing cues, achieving a halved character error rate compared to previous state‑of‑the‑art methods. These results underscore the dataset’s and model’s value for advancing sign language research and automated annotation pipelines.
By Alyssa Chan, Taein Kwon, Andrew Zisserman
arXiv:2608. 09045v1 Announce Type: cross Abstract: Recent advances in sign language (SL) research have shown a trend toward unifying multiple sign language understanding (SLU) subtasks, such as isolated sign language recognition (ISLR), continuous sign language recognition (CSLR), and sign language translation (SLT), within a single framework, leading to substantial progress.
By Xiao Liu, Shiwei Gan, Yafeng Yin, Jiaxin Yin, Bowen Guo, Yaqi Sun, Zhiwei Jiang, Lei Xie
The paper introduces the Sequential Spatio-Temporal Attention Network (SSTAN), a Transformer-based architecture that replaces traditional Graph Convolutional Networks for sign language recognition. SSTAN uses a hierarchical, stacked design with Spatial Multi-Head Attention to model joint relationships within frames and Temporal Multi-Head Attention to capture long-range dependencies across frames, eliminating the need for predefined skeletal graphs. Experiments on large-scale datasets (WLASL, JSL, KSL) show that SSTAN, trained from scratch, achieves state‑of‑the‑art performance in fingerspelling categories and outperforms other skeleton‑only methods on WLASL, highlighting its data efficiency and ability to learn complex spatio‑temporal patterns.
By Koki Hirooka, Abu Saleh Musa Miah, Tatsuya Murakami, Md. Al Mehedi Hasan, Yong Seok Hwang, Jungpil Shin
arXiv:2605.20588v2 Announce Type: replace
Abstract: Sign language translation has made substantial progress between sign and spoken languages, while translation across sign languages remains less exp...
By Zetian Wu, Bowen Xie, Wuyang Meng, Milan Gautam, Stefan Lee, Liang Huang
arXiv:2606. 19352v1 Announce Type: cross Abstract: Sign languages are expressive visual languages used by Deaf and Hard-of-Hearing (DHH) communities.
By Yiming Ni, Zhi-Qi Cheng, Jiayu Li, Wei Cheng
The paper introduces BdSLIG, the first Bengali Sign Language Instruction Generation dataset, aimed at evaluating Vision Language Models on under-resourced SLIG tasks and long-tail visual concepts. It proposes Sign Parameter-Infused (SPI) prompting, which embeds standard sign parameters such as hand shape, motion, and orientation into textual prompts to improve zero-shot performance and produce more structured, reproducible instructions. The work seeks to promote inclusivity and advance sign language learning systems for under-resourced communities.
By Md Tariquzzaman, Md Farhan Ishmam, Saiyma Sittul Muna, Md Kamrul Hasan, Hasan Mahmud
The paper introduces AttnSign, a vision‑language model that improves sign language translation by steering spatial‑temporal attention. It first supervises attention on sign‑relevant regions such as faces and hands in each frame, then uses an RL‑based motion‑cadence method to focus on keyframes. Experiments on How2Sign and OpenASL show AttnSign consistently outperforms existing methods.
By Meibo Hu, Guohao Sun, Annemarie D. Ross, Sheng Li, Zhiqiang Tao
The paper argues that BLEU-4, the prevailing metric for sign language translation (SLT), may not accurately reflect sign language proficiency because SLT models can exploit spurious correlations and spoken-language priors. By evaluating six SLT models on Phoenix-2014T and CSL-Daily, the authors show that higher BLEU-4 scores do not necessarily indicate better spatio-temporal understanding. They propose a new open-weight LLM QA protocol inspired by language-learning assessment, which better preserves salient content, aligns more closely with human rankings, and reveals differences between gloss-free and gloss-supervised systems that BLEU-4 obscures.
By Oline Ranum, Edward Fish, Simon Hadfield, Richard Bowden