{"ID":2847789,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.00270","arxiv_id":"2511.00270","title":"POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation","abstract":"Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machine translation for sign languages. We propose POSESTITCH-SLT, a novel pre-training scheme that is inspired by linguistic-templates-based sentence generation technique. With translation comparison on two sign language datasets, How2Sign and iSign, we show that a simple transformer-based encoder-decoder architecture outperforms the prior art when considering template-generated sentence pairs in training. We achieve BLEU-4 score improvements from 1.97 to 4.56 on How2Sign and from 0.55 to 3.43 on iSign, surpassing prior state-of-the-art methods for pose-based gloss-free translation. The results demonstrate the effectiveness of template-driven synthetic supervision in low-resource sign language settings.","short_abstract":"Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machine translation for sign languages. We propose POSESTITCH-SLT, a novel pre-training scheme that is ins...","url_abs":"https://arxiv.org/abs/2511.00270","url_pdf":"https://arxiv.org/pdf/2511.00270v1","authors":"[\"Abhinav Joshi\",\"Vaibhav Sharma\",\"Sanjeet Singh\",\"Ashutosh Modi\"]","published":"2025-10-31T21:44:59Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.CV\",\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}