{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T13:07:52Z","timestamp":1784725672356,"version":"3.55.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00530-026-02316-8","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T07:32:08Z","timestamp":1780731128000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Signing, not just spelling: a syntactically-aware sign language generation system with large language models"],"prefix":"10.1007","volume":"32","author":[{"given":"Zhenxun","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haodong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kangwen","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,6]]},"reference":[{"key":"2316_CR1","doi-asserted-by":"crossref","unstructured":"Amballa, A., Akkinapalli, G., Muralikrishnan, V.: Ls-gan: human motion synthesis with latent-space gans. In: Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops (2025)","DOI":"10.1109\/WACVW65960.2025.00039"},{"issue":"6","key":"2316_CR2","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1111\/cgf.13310","volume":"37","author":"A Aristidou","year":"2018","unstructured":"Aristidou, A., Lasenby, J., Chrysanthou, Y., Shamir, A.: Inverse kinematics techniques in computer graphics: a survey. Comput. Graph. Forum 37(6), 35\u201358 (2018)","journal-title":"Comput. Graph. Forum"},{"key":"2316_CR3","unstructured":"Bai, J., Bai, S., Chu, Y., Cui, Z., Dang, K., Deng, X., Fan, Y., Ge, W., Han, Y., Huang, F. et al. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"2316_CR4","unstructured":"Baker, C., Padden, C.: Focusing on the nonmanual components of american sign language. In: Siple, P. (ed.) Understanding language through sign language research, pp. 27\u201357. Academic Press, Amsterdam (1978)"},{"key":"2316_CR5","first-page":"1877","volume":"33","author":"TB Brown","year":"2020","unstructured":"Brown, T.B., Mann, B., Ryder, N., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2316_CR6","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Hadfield, S., Koller, O., Ney, H., Bowden, R.: Neural sign language translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00812"},{"key":"2316_CR7","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Hadfield, S., Koller, O., Ney, H., Bowden, R.: Neural sign language translation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7784\u20137793 (2018)","DOI":"10.1109\/CVPR.2018.00812"},{"key":"2316_CR8","unstructured":"Camgoz, N.C., Koller, O., Hadfield, S., Bowden, R.: Sign language transformers: Joint end-to-end sign language recognition and translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)"},{"key":"2316_CR9","doi-asserted-by":"crossref","unstructured":"Chen, F., Zhang, D., Chen, X., Shi, J., Xu, S., Xu, B.: Unsupervised and pseudo-supervised vision-language alignment in visual dialog. In: Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 4142\u20134153 (2022)","DOI":"10.1145\/3503161.3547776"},{"key":"2316_CR10","doi-asserted-by":"crossref","unstructured":"Duarte, A., Palaskar, S., Ventura, L., Ghadiyaram, D., DeHaan, K., Metze, F., Torres, J., Giro-i Nieto, X.: How2sign: a large-scale multimodal dataset for continuous american sign language. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2735\u20132744 (2021)","DOI":"10.1109\/CVPR46437.2021.00276"},{"issue":"1","key":"2316_CR11","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s00530-022-00980-0","volume":"29","author":"S Dubey","year":"2023","unstructured":"Dubey, S., Dixit, M.: A comprehensive survey on human pose estimation approaches. Multimedia Syst. 29(1), 167\u2013195 (2023)","journal-title":"Multimedia Syst."},{"key":"2316_CR12","unstructured":"Gu, Y., Zheng, Y., Swerts, M.: Does mandarin spatial metaphor for time influence Chinese deaf signers\u2019 spatio-temporal reasoning? In: Proceedings of the Annual Meeting of the Cognitive Science Society, 39 (2017)"},{"key":"2316_CR13","doi-asserted-by":"crossref","unstructured":"Guo, C., Zuo, X., Wang, S., Zou, S., Sun, Q., Deng, A., Gong, M., Cheng, L.: Action2motion: Conditioned generation of 3d human motions. In: Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 2021\u20132029 (2020)","DOI":"10.1145\/3394171.3413635"},{"key":"2316_CR14","first-page":"43","volume":"101","author":"L Hao","year":"2019","unstructured":"Hao, L.: Functions of mouthing in the interrogatives of Chinese sign language. Senri Ethnol. Stud. 101, 43\u201356 (2019)","journal-title":"Senri Ethnol. Stud."},{"issue":"2","key":"2316_CR15","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., et al.: Lora: low-rank adaptation of large language models. ICLR 1(2), 3 (2022)","journal-title":"ICLR"},{"issue":"2","key":"2316_CR16","first-page":"467","volume":"51","author":"J Huang","year":"2024","unstructured":"Huang, J., et al.: Eliciting and improving the causal reasoning abilities of large language models with conditional statements. Comput. Linguist. 51(2), 467\u2013501 (2024)","journal-title":"Comput. Linguist."},{"key":"2316_CR17","doi-asserted-by":"crossref","unstructured":"Huang, W., Pan, W., Zhao, Z, Tian, Q.: Towards fast and high-quality sign language production. In: Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 3172\u20133181 (2021)","DOI":"10.1145\/3474085.3475463"},{"key":"2316_CR18","doi-asserted-by":"crossref","unstructured":"Islam, M., Huang, T., Ahn, E., Naseem, U.: Multimodal generative ai with autoregressive llms for human motion understanding and generation: A way forward. arXiv preprint arXiv:2506.03191 (2025)","DOI":"10.1016\/j.inffus.2026.104435"},{"issue":"3\u20134","key":"2316_CR19","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1556\/ALing.55.2008.3-4.2","volume":"55","author":"M Krifka","year":"2008","unstructured":"Krifka, M.: Basic notions of information structure. Acta Linguistica Hungarica55(3\u20134), 243\u2013276 (2008)","journal-title":"Acta Linguistica Hungarica"},{"key":"2316_CR20","doi-asserted-by":"crossref","unstructured":"Li, D., Xu, C., Liu, L., Zhong, Y., Wang, R., Petersson, L., Li, H.: Transcribing natural languages for the deaf via neural editing programs. In: Proceedings of the AAAI conference on artificial intelligence (AAAI-22), 36, 11991\u201311999 (2022)","DOI":"10.1609\/aaai.v36i11.21457"},{"key":"2316_CR21","unstructured":"Liddell, S.K.: An investigation into the syntactic structure of American Sign Language. PhD thesis, University of California, San Diego (1977)"},{"key":"2316_CR22","doi-asserted-by":"crossref","unstructured":"Liddell, S.K.: American Sign Language Syntax. Mouton (1980)","DOI":"10.1515\/9783112418260"},{"issue":"1\u20132","key":"2316_CR23","first-page":"1","volume":"37","author":"D Lillo-Martin","year":"2011","unstructured":"Lillo-Martin, D., Meier, R.P.: On the linguistic status of \u2018agreement\u2019 in signed languages. Theoret. Linguist. 37(1\u20132), 1\u201353 (2011)","journal-title":"Theoret. Linguist."},{"key":"2316_CR24","volume-title":"The Syntax of American Sign Language: functional Categories and Hierarchical Structure","author":"C Neidle","year":"2000","unstructured":"Neidle, C., Kegl, J., MacLaughlin, D., Bahan, B., Lee, R.G.: The Syntax of American Sign Language: functional Categories and Hierarchical Structure. MIT Press, Cambridge (2000)"},{"key":"2316_CR25","volume-title":"Interaction of Morphology and Syntax in American Sign Language","author":"CA Padden","year":"1988","unstructured":"Padden, C.A.: Interaction of Morphology and Syntax in American Sign Language. Garland Press, Massachusetts (1988)"},{"issue":"5000","key":"2316_CR26","doi-asserted-by":"publisher","first-page":"1493","DOI":"10.1126\/science.2006424","volume":"251","author":"LA Petitto","year":"1991","unstructured":"Petitto, L.A., Marentette, P.F.: Babbling in the manual mode: evidence for the ontogeny of language. Science 251(5000), 1493\u20131496 (1991)","journal-title":"Science"},{"key":"2316_CR27","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Temos: generating diverse human motions from textual descriptions. In: European Conference on Computer Vision (ECCV), pp. 216\u2013234. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"2316_CR28","unstructured":"Qwen Team. Qwen technical report. Technical Report 2309.16609, arXiv (2023)"},{"key":"2316_CR29","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training. OpenAI (2018)"},{"issue":"3","key":"2316_CR30","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1002\/lnc3.326","volume":"6","author":"W Sandler","year":"2012","unstructured":"Sandler, W.: The phonological organization of sign languages. Lang. Linguist Compass 6(3), 161\u2013184 (2012)","journal-title":"Lang. Linguist Compass"},{"key":"2316_CR31","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139163910","volume-title":"Sign Language and Linguistic Universals","author":"W Sandler","year":"2006","unstructured":"Sandler, W., Lillo-Martin, D.: Sign Language and Linguistic Universals. Cambridge University Press, Cambridge (2006)"},{"key":"2316_CR32","doi-asserted-by":"crossref","unstructured":"Saunders, B., Camgoz, N.C., Bowden, R. :Progressive transformers for end-to-end sign language production. In: European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58621-8_40"},{"key":"2316_CR33","doi-asserted-by":"publisher","first-page":"55565","DOI":"10.52202\/075280-2425","volume":"36","author":"R Schaeffer","year":"2023","unstructured":"Schaeffer, R., Miranda, B., Koyejo, S.: Are emergent abilities of large language models a mirage? Adv. Neural. Inf. Process. Syst. 36, 55565\u201355581 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2316_CR34","doi-asserted-by":"crossref","unstructured":"Song, Y., Shi, S., Li, J., Zhang, H.: Directional skip-gram: Explicitly distinguishing left and right context for word embeddings. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 2 (Short Papers), pp. 175\u2013180 (2018)","DOI":"10.18653\/v1\/N18-2028"},{"key":"2316_CR35","unstructured":"Stokoe, W.C.: Sign language structure: an outline of the visual communication systems of the american deaf. Studies in Linguistics, Occasional Papers 8. University of Buffalo (1960)"},{"key":"2316_CR36","volume-title":"A Dictionary of American Sign Language on Linguistic Principles","author":"WC Stokoe","year":"1965","unstructured":"Stokoe, W.C., Casterline, D.C., Croneberg, C.G.: A Dictionary of American Sign Language on Linguistic Principles. Gallaudet College Press, Washington (1965)"},{"issue":"4","key":"2316_CR37","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1007\/s11263-019-01281-2","volume":"128","author":"S Stoll","year":"2020","unstructured":"Stoll, S., Camgoz, N.C., Hadfield, S., Bowden, R.: Text2sign: towards sign language production using neural machine translation and generative adversarial networks. Int. J. Comput. Vision 128(4), 891\u2013908 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"2316_CR38","doi-asserted-by":"publisher","first-page":"4433","DOI":"10.1109\/TMM.2021.3117124","volume":"24","author":"S Tang","year":"2021","unstructured":"Tang, S., Guo, D., Hong, R., Wang, M.: Graph-based multimodal sequential embedding for sign language translation. IEEE Trans. Multimedia 24, 4433\u20134445 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"2316_CR39","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., Bermano,A.H.: Human motion diffusion model. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"2316_CR40","unstructured":"Touvron, H., Lavril, T., Izacard, G. et al. Llama: Open and efficient foundation language models (2023)"},{"key":"2316_CR41","unstructured":"Unity Technologies. Unity real-time development platform. https:\/\/unity.com (2022). Accessed 17 Oct 2025"},{"issue":"6","key":"2316_CR42","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/s00530-024-01505-7","volume":"30","author":"S Wang","year":"2024","unstructured":"Wang, S., Guo, L., Xue, W.: Dynamical semantic enhancement network for continuous sign language recognition. Multimedia Syst. 30(6), 313 (2024)","journal-title":"Multimedia Syst."},{"key":"2316_CR43","unstructured":"Wei, J.: Emergent abilities of large language models. Blog post (2022)"},{"key":"2316_CR44","unstructured":"Wilbur, R.B.: Phonological and prosodic layering of nonmanuals in american sign language. In: Emmorey, K., Lane, H. (Eds.) The signs of language revisited: an anthology to honor Ursula Bellugi and Edward Klima, pp. 215\u2013244. Lawrence Erlbaum Associates (2000)"},{"issue":"1","key":"2316_CR45","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s00530-025-02100-0","volume":"32","author":"Y Yang","year":"2026","unstructured":"Yang, Y., Wang, Q., Wang, Q., Chen, S.: Angle and graph topology enhanced framework with dual-channel mixed token progressing unit for sign language production. Multimedia Syst. 32(1), 33 (2026)","journal-title":"Multimedia Syst."},{"key":"2316_CR46","doi-asserted-by":"crossref","unstructured":"Yin, A., Read, J.: Better sign language translation with data augmentation. In: Proceedings of the International Workshop on Sign Language Translation and Avatar Technology (SLTAT) (2020)","DOI":"10.18653\/v1\/2020.coling-main.525"},{"key":"2316_CR47","doi-asserted-by":"crossref","unstructured":"Yu, T., Wang, J., Wang, J., Luo, J., Zhou, G.: Towards emotion-enriched text-to-motion generation via llm-guided limb-level emotion manipulating. In: Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 612\u2013621 (2024)","DOI":"10.1145\/3664647.3681487"},{"key":"2316_CR48","doi-asserted-by":"crossref","unstructured":"Zeng, A., Yang, L., Ju, X., Li, J., Wang, J., Xu, Q.: Smoothnet: a plug-and-play network for refining human poses in videos. In: European Conference on Computer Vision, pp. 625\u2013642. Springer (2022)","DOI":"10.1007\/978-3-031-20065-6_36"},{"key":"2316_CR49","unstructured":"Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., Liu, Z.: Motiondiffuse: text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001 (2022)"},{"key":"2316_CR50","unstructured":"Zhang, X., Duh, K.: Approaching sign language gloss translation as a low-resource machine translation task. In: Proceedings of the 1st International Workshop on Automatic Translation for Signed and Spoken Languages (AT4SSL), pp. 60\u201370 (2021)"},{"key":"2316_CR51","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1109\/TMM.2021.3059098","volume":"24","author":"H Zhou","year":"2021","unstructured":"Zhou, H., Zhou, W., Zhou, Y., Li, H.: Spatial-temporal multi-cue network for sign language recognition and translation. IEEE Trans. Multimedia 24, 768\u2013779 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"2316_CR52","doi-asserted-by":"crossref","unstructured":"Zhu, W., Ma, X., Ro, D., Ci, H., Zhang, J., Shi, J., Gao, F., Tian, Q., Wang, Y.: Human motion generation: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)","DOI":"10.1109\/TPAMI.2023.3330935"},{"key":"2316_CR53","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1109\/TMM.2020.3001506","volume":"23","author":"X Zuo","year":"2020","unstructured":"Zuo, X., Wang, S., Zheng, J., Weiwei, Yu., Gong, M., Yang, R., Cheng, L.: Sparsefusion: dynamic human avatar modeling from sparse RGBD images. IEEE Trans. Multimedia 23, 1617\u20131629 (2020)","journal-title":"IEEE Trans. Multimedia"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02316-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02316-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02316-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T12:56:59Z","timestamp":1784725019000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02316-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,6]]},"references-count":53,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["2316"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02316-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,6]]},"assertion":[{"value":"8 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"327"}}