Enhancing Sequence-to-Sequence Modelling for RDF triples to Natural Text
Oriol Domingo, David Bergés, Roser Cantenys, Roger Creus, José A. R. Fonollosa
Abstract
establishes key guidelines on how, which and when Machine Translation (MT) techniques are worth applying to RDF-to-Text task. Not only do we apply and compare the most prominent MT architecture, the Transformer, but we also analyze state-of-the-art techniques such as Byte Pair Encoding or Back Translation to demonstrate an improvement in generalization. In addition, we empirically show how to tailor these techniques to enhance models relying on learned embeddings rather than using pretrained ones. Automatic metrics suggest that Back Translation can significantly improve model performance up to 7 BLEU points, hence, opening a window for surpassing state-of-the-art results with appropriate architectures.- Anthology ID:
- 2020.webnlg-1.5
- Volume:
- Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+)
- Month:
- 12
- Year:
- 2020
- Address:
- Dublin, Ireland (Virtual)
- Venue:
- WebNLG
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 40–47
- Language:
- URL:
- https://aclanthology.org/2020.webnlg-1.5
- DOI:
- Cite (ACL):
- Oriol Domingo, David Bergés, Roser Cantenys, Roger Creus, and José A. R. Fonollosa. 2020. Enhancing Sequence-to-Sequence Modelling for RDF triples to Natural Text. In Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+), pages 40–47, Dublin, Ireland (Virtual). Association for Computational Linguistics.
- Cite (Informal):
- Enhancing Sequence-to-Sequence Modelling for RDF triples to Natural Text (Domingo et al., WebNLG 2020)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2020.webnlg-1.5.pdf
- Code
- uridr/rdf-textgeneration
- Data
- WebNLG