Syntax-aware Transformers for Neural Machine Translation: The Case of Text to Sign Gloss Translation

Santiago Egea Gómez, Euan McGill, Horacio Saggion


Abstract
It is well-established that the preferred mode of communication of the deaf and hard of hearing (DHH) community are Sign Languages (SLs), but they are considered low resource languages where natural language processing technologies are of concern. In this paper we study the problem of text to SL gloss Machine Translation (MT) using Transformer-based architectures. Despite the significant advances of MT for spoken languages in the recent couple of decades, MT is in its infancy when it comes to SLs. We enrich a Transformer-based architecture aggregating syntactic information extracted from a dependency parser to word-embeddings. We test our model on a well-known dataset showing that the syntax-aware model obtains performance gains in terms of MT evaluation metrics.
Anthology ID:
2021.bucc-1.4
Volume:
Proceedings of the 14th Workshop on Building and Using Comparable Corpora (BUCC 2021)
Month:
September
Year:
2021
Address:
Online (Virtual Mode)
Editors:
Reinhard Rapp, Serge Sharoff, Pierre Zweigenbaum
Venue:
BUCC
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
18–27
Language:
URL:
https://aclanthology.org/2021.bucc-1.4
DOI:
Bibkey:
Cite (ACL):
Santiago Egea Gómez, Euan McGill, and Horacio Saggion. 2021. Syntax-aware Transformers for Neural Machine Translation: The Case of Text to Sign Gloss Translation. In Proceedings of the 14th Workshop on Building and Using Comparable Corpora (BUCC 2021), pages 18–27, Online (Virtual Mode). INCOMA Ltd..
Cite (Informal):
Syntax-aware Transformers for Neural Machine Translation: The Case of Text to Sign Gloss Translation (Egea Gómez et al., BUCC 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.bucc-1.4.pdf
Code
 lastus-taln-upf/syntax-aware-transformer-text2gloss