Translating Spanish into Spanish Sign Language: Combining Rules and Data-driven Approaches

Luis Chiruzzo, Euan McGill, Santiago Egea-Gómez, Horacio Saggion


Abstract
This paper presents a series of experiments on translating between spoken Spanish and Spanish Sign Language glosses (LSE), including enriching Neural Machine Translation (NMT) systems with linguistic features, and creating synthetic data to pretrain and later on finetune a neural translation model. We found evidence that pretraining over a large corpus of LSE synthetic data aligned to Spanish sentences could markedly improve the performance of the translation models.
Anthology ID:
2022.loresmt-1.10
Volume:
Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Atul Kr. Ojha, Chao-Hong Liu, Ekaterina Vylomova, Jade Abbott, Jonathan Washington, Nathaniel Oco, Tommi A Pirinen, Valentin Malykh, Varvara Logacheva, Xiaobing Zhao
Venue:
LoResMT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
75–83
Language:
URL:
https://aclanthology.org/2022.loresmt-1.10
DOI:
Bibkey:
Cite (ACL):
Luis Chiruzzo, Euan McGill, Santiago Egea-Gómez, and Horacio Saggion. 2022. Translating Spanish into Spanish Sign Language: Combining Rules and Data-driven Approaches. In Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022), pages 75–83, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
Translating Spanish into Spanish Sign Language: Combining Rules and Data-driven Approaches (Chiruzzo et al., LoResMT 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.loresmt-1.10.pdf