Abstract
In recent years, referring expression genera- tion algorithms were inspired by game theory and probability theory. In this paper, an al- gorithm is designed for the generation of re- ferring expressions (REG) that base on both models by integrating maximization of utilities into the content determination process. It im- plements cognitive models for assessing visual salience of objects and additional features. In order to evaluate the algorithm properly and validate the applicability of existing models and evaluative information criteria, both, pro- duction and comprehension studies, are con- ducted using a complex domain of objects, pro- viding new directions of approaching the eval- uation of REG algorithms.- Anthology ID:
- 2020.inlg-1.36
- 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:
- 296–305
- Language:
- URL:
- https://aclanthology.org/2020.inlg-1.36
- DOI:
- 10.18653/v1/2020.inlg-1.36
- Cite (ACL):
- Maurice Langner. 2020. OMEGA : A probabilistic approach to referring expression generation in a virtual environment. In Proceedings of the 13th International Conference on Natural Language Generation, pages 296–305, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- OMEGA : A probabilistic approach to referring expression generation in a virtual environment (Langner, INLG 2020)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2020.inlg-1.36.pdf