Hybrid translation for sign languages: combining rule-based and neural machine translation in a low-resource scenario.
Machine translation into sign language (or Sign Language Machine Translation—SLMT) presents a promising and emerging solution for overcoming barriers to information access and communication among Deaf individuals. However, the development of such systems is particularly challenging due to the low-re...
| Published in: | Language Resources & Evaluation Vol. 59; no. 4; pp. 4155 - 4193 |
|---|---|
| Main Authors: | , , , , , , , , |
| Format: | Article |
| Published: |
Springer Nature
Dec2025
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=189912046&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 189912046 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 1574020X 179V jtl: Language Resources & Evaluation issn: 1574020X maglogo: N pubinfo: dt: Dec2025 vid: 59 iid: 4 pid: 237 pub: Springer Nature artinfo: ui: 189912046 10.1007/s10579-025-09874-9 ppf: 4155 ppct: 38 formats: tig: atl: Hybrid translation for sign languages: combining rule-based and neural machine translation in a low-resource scenario. aug: au: Silva, Diego R. B. da Lima, Manuella A. C. B. Moreira, Samuel de M. Campos, Virginia P. Costa, Renan P. O. de Araújo, Tiago M. U. Costa, Rostand E. O. de Souza, Daniel F. L. de Albuquerque, Dilainne D. affil: https://ror.org/00p9vpz11 Digital Video Applications Lab (LAVID), Federal University of Paraíba (UFPB), João Pessoa, Paraíba, Brazil https://ror.org/04wn09761 Federal University of Rio Grande do Norte (UFRN), Natal, Rio Grande do Norte, Brazil su: Sign language Machine translating Rule-based programming sug: subj: Sign language Machine translating Rule-based programming keyword: Communication and Culture Linguistics Information and Computing Sciences Artificial Intelligence and Image Processing Datasets Language Machine translation Multimedia platforms ab: Machine translation into sign language (or Sign Language Machine Translation—SLMT) presents a promising and emerging solution for overcoming barriers to information access and communication among Deaf individuals. However, the development of such systems is particularly challenging due to the low-resource nature of sign languages, including Brazilian Sign Language (Libras), which is the focus of this study. To address this challenge, we propose a hybrid machine translation approach for Brazilian Portuguese to Libras. Our solution combines text-to-gloss translation, integrating both rule-based and neural machine translation methods. The advantage of this strategy lies in using rule-based preprocessing for deterministic tasks, while a neural data-driven model handles more complex tasks, such as word-sense disambiguation, directional verbs, intensifier adverbs, and negative incorporation. This approach enhances both the fluency and naturalness of the translations. To support this approach, we constructed a new parallel corpus consisting of 70,000 sentence pairs (Brazilian Portuguese and corresponding Libras glosses). We also conducted computational experiments and user tests to compare our hybrid approach with the existing rule-based version of VLibras, which is currently deployed across thousands of Brazilian websites. The results indicate that our approach outperforms the current version, offering a promising direction for advancing SLMT solutions in low-resource contexts. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2025 holdings: @attributes: islocal: N |
|---|