Syntax-aware transformers for neural machine translation: the case of text to sign gloss translation

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Egea Gómez, Santiago
• dc.contributor.author McGill, Euan
• dc.contributor.author Saggion, Horacio
• dc.date.accessioned 2022-01-12T10:46:33Z
• dc.date.available 2022-01-12T10:46:33Z
• dc.date.issued 2021
• dc.description Comunicació presentada a: 14th Workshop on Building and Using Comparable Corpora (BUCC) celebrat el 6 de setembre de 2021 de manera virtual.
• dc.description.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.
• dc.description.sponsorship This work has been conducted within the SignON project. SignON is a Horizon 2020 project, funded under the Horizon 2020 program ICT-57-2020 - ”An empowering, inclusive, Next Generation Internet” with Grant Agreement number 101017255.
• dc.format.mimetype application/pdf
• dc.identifier.citation Egea Gómez S, McGill E, Saggion H. Syntax-aware transformers for neural machine translation: the case of text to sign gloss translation. In: Rapp R, Sharoff S, Zweigenbaum P, editors. Proceedings of the 14th Workshop on Building and Using Comparable Corpora (BUCC 2021) in conjunction with the International Conference on Recent Advances in Natural Language Processing (RANLP 2021); 2021 Sep 6. Shoumen: INCOMA Ltd.; 2021. p. 18-27. DOI: 10.26615/978-954-452-076-2_004
• dc.identifier.doi http://dx.doi.org/10.26615/978-954-452-076-2_004
• dc.identifier.isbn 978-954-452-072-4
• dc.identifier.issn 2603-2813
• dc.identifier.uri http://hdl.handle.net/10230/52195
• dc.language.iso eng
• dc.publisher ACL (Association for Computational Linguistics)
• dc.relation.isreferencedby https://github.com/lastus-taln-upf/syntax-aware-transformer-text2gloss
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/101017255
• dc.rights © ACL, Creative Commons Attribution 4.0 License
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri https://creativecommons.org/licenses/by/4.0/
• dc.title Syntax-aware transformers for neural machine translation: the case of text to sign gloss translation
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion