Better Translation + Split and Generate for Multilingual RDF-to-Text (WebNLG 2023)

Nalin Kumar, Saad Obaid Ul Islam, Ondrej Dusek


Abstract
This paper presents system descriptions of our submitted outputs for WebNLG Challenge 2023. We use mT5 in multi-task and multilingual settings to generate more fluent and reliable verbalizations of the given RDF triples. Furthermore, we introduce a partial decoding technique to produce more elaborate yet simplified outputs. Additionally, we demonstrate the significance of employing better translation systems in creating training data.
Anthology ID:
2023.mmnlg-1.8
Volume:
Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023)
Month:
September
Year:
2023
Address:
Prague, Czech Republic
Editors:
Albert Gatt, Claire Gardent, Liam Cripwell, Anya Belz, Claudia Borg, Aykut Erdem, Erkut Erdem
Venues:
MMNLG | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
73–79
Language:
URL:
https://aclanthology.org/2023.mmnlg-1.8
DOI:
Bibkey:
Cite (ACL):
Nalin Kumar, Saad Obaid Ul Islam, and Ondrej Dusek. 2023. Better Translation + Split and Generate for Multilingual RDF-to-Text (WebNLG 2023). In Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023), pages 73–79, Prague, Czech Republic. Association for Computational Linguistics.
Cite (Informal):
Better Translation + Split and Generate for Multilingual RDF-to-Text (WebNLG 2023) (Kumar et al., MMNLG-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.mmnlg-1.8.pdf