Abstract
This study describes the approach developed by the Tilburg University team to the shallow task of the Multilingual Surface Realization Shared Task 2018 (SR18). Based on (Castro Ferreira et al., 2017), the approach works by first preprocessing an input dependency tree into an ordered linearized string, which is then realized using a statistical machine translation model. Our approach shows promising results, with BLEU scores above 50 for 5 different languages (English, French, Italian, Portuguese and Spanish) and above 35 for the Dutch language.- Anthology ID:
- W18-3604
- Volume:
- Proceedings of the First Workshop on Multilingual Surface Realisation
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 35–38
- Language:
- URL:
- https://aclanthology.org/W18-3604
- DOI:
- 10.18653/v1/W18-3604
- Cite (ACL):
- Thiago Castro Ferreira, Sander Wubben, and Emiel Krahmer. 2018. Surface Realization Shared Task 2018 (SR18): The Tilburg University Approach. In Proceedings of the First Workshop on Multilingual Surface Realisation, pages 35–38, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Surface Realization Shared Task 2018 (SR18): The Tilburg University Approach (Castro Ferreira et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W18-3604.pdf
- Code
- ThiagoCF05/Dep2Text