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
arXiv:2606. 08056v1 Announce Type: cross Abstract: Sign language models are predominantly trained with gloss-sequence or text supervision, thereby under-modeling non-lexical and productive constructions.
By Oline Ranum, Simon Hadfield, Richard Bowden
SignRAG is a unified framework for gloss‑free sign language translation that combines hierarchical pretraining, target‑domain retrieval augmentation, and retrieval‑aware reinforcement fine‑tuning. It first learns linguistically grounded sign representations, aligns a sign encoder with a decoder‑only large language model, and then uses a retrieval gallery to provide instance‑specific translation cues. Retrieval Utility‑Guided Reinforcement Fine‑Tuning (RUG‑RFT) balances translation quality and retrieval usefulness, leading to state‑of‑the‑art results, including the first gloss‑free approach to outperform gloss‑supervised methods on CSL‑Daily.
By Zhi Rao, Yucheng Zhou, Qianran Sun, Yiqing Huang, Longcan Yuan, Jiayi Hou, Chengwen Yao, Lin Cheng, Donghui Sun, Xiaoxin Chen, Jun Wan
arXiv:2605. 31393v2 Announce Type: replace-cross Abstract: Sign language translation (SLT) remains constrained by the limited availability of paired sign-video/text corpora and by the heavy-tailed vocabularies typical of real-world datasets.
By Pedro Dal Bianco, Jean Paul Nunes Reinhold, Oscar Stanchi, Facundo Quiroga, Franco Ronchetti, Ulisses Brisolara Corr\^ea
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
The paper introduces discourse dependency (DDP) as a continuous measure of translation difficulty based on how far back a segment must look to resolve references. DDP is computed from named entity re‑mentions and pronominal coreference, and is validated against gold coreference with high reliability. Applying DDP to recent WMT benchmarks reveals a bias toward low‑DDP segments, and experiments show that as DDP increases, no current context‑injection strategy matches human post‑editing quality.
By Ahrii Kim, Chanjun Park, Seong-heum Kim