Abstract
Surface realisation is the last but not the least phase of Natural Language Generation, which aims to produce high-quality natural language text based on meaning representations. In this article, we present our work on SimpleNLG-TI, a Tibetan surface realiser, which follows the design paradigm of SimpleNLG-EN. SimpleNLG-TI is built up by our investigation of the core features of Tibetan morphology and syntax. Through this work, we provide a robust and flexible surface realiser for Tibetan generation systems.- Anthology ID:
- 2020.inlg-1.12
- Volume:
- Proceedings of the 13th International Conference on Natural Language Generation
- Month:
- December
- Year:
- 2020
- Address:
- Dublin, Ireland
- Editors:
- Brian Davis, Yvette Graham, John Kelleher, Yaji Sripada
- Venue:
- INLG
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 86–90
- Language:
- URL:
- https://aclanthology.org/2020.inlg-1.12
- DOI:
- 10.18653/v1/2020.inlg-1.12
- Cite (ACL):
- Zewang Kuanzhuo, Li Lin, and Zhao Weina. 2020. SimpleNLG-TI: Adapting SimpleNLG to Tibetan. In Proceedings of the 13th International Conference on Natural Language Generation, pages 86–90, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- SimpleNLG-TI: Adapting SimpleNLG to Tibetan (Kuanzhuo et al., INLG 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.inlg-1.12.pdf