Graph-based generation of referring expressions
Computational Linguistics
ENLG '09 Proceedings of the 12th European Workshop on Natural Language Generation
Cross-linguistic attribute selection for REG: comparing Dutch and English
INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Does size matter: how much data is required to train a REG algorithm?
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Computational generation of referring expressions: A survey
Computational Linguistics
Hi-index | 0.00 |
We describe a graph-based generation system that participated in the TUNA attribute selection and realisation task of the REG 2008 Challenge. Using a stochastic cost function (with certain properties for free), and trying attributes from cheapest to more expensive, the system achieves overall .76 DICE and .54 MASI scores for attribute selection on the development set. For realisation, it turns out that in some cases higher attribute selection accuracy leads to larger differences between system-generated and human descriptions.