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.
|Title of host publication||Proceedings of the 5th International Natural Language Generation Conference (INLG 2008)|
|Place of Publication||USA|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||3|
|ISBN (Print)||not assigned|
|Publication status||Published - Jun 2008|
|Publisher||The Association for Computational Linguistics|
Krahmer, E., Theune, M., Viethen, J., & Hendrickx, I. (2008). GRAPH: The Costs of Redundancy in Referring Expressions. In Proceedings of the 5th International Natural Language Generation Conference (INLG 2008) (pp. 227-229). USA: Association for Computational Linguistics (ACL).