Abstract
This paper describes the submission by the NILC Computational Linguistics research group of the University of São Paulo/Brazil to the Track 1 of the Surface Realization Shared Task (SRST Track 1). We present a neural-based method that works at the syntactic level to order the words (which we refer by NILC-SWORNEMO, standing for “Syntax-based Word ORdering using NEural MOdels”). Additionally, we apply a bottom-up approach to build the sentence and, using language-specific lexicons, we produce the proper word form of each lemma in the sentence. The results obtained by our method outperformed the average of the results for English, Portuguese and Spanish in the track.- Anthology ID:
- W18-3608
- 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:
- 58–64
- Language:
- URL:
- https://aclanthology.org/W18-3608
- DOI:
- 10.18653/v1/W18-3608
- Cite (ACL):
- Marco Antonio Sobrevilla Cabezudo and Thiago Pardo. 2018. NILC-SWORNEMO at the Surface Realization Shared Task: Exploring Syntax-Based Word Ordering using Neural Models. In Proceedings of the First Workshop on Multilingual Surface Realisation, pages 58–64, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- NILC-SWORNEMO at the Surface Realization Shared Task: Exploring Syntax-Based Word Ordering using Neural Models (Sobrevilla Cabezudo & Pardo, ACL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W18-3608.pdf