Paper: USP-EACH Frequency-based Greedy Attribute Selection for Referring Expressions Generation

ACL ID W08-1135
Title USP-EACH Frequency-based Greedy Attribute Selection for Referring Expressions Generation
Venue International Conference on Natural Language Generation
Session Main Conference
Year 2008
Authors

Both greedy and domain-oriented REG algo- rithms have significant strengths but tend to perform poorly according to humanlikeness criteria as measured by, e.g., Dice scores. In this work we describe an attempt to combine both perspectives into a single attribute selec- tion strategy to be used as part of the Dale & Reiter Incremental algorithm in the REG Challenge 2008, and the results in both Furni- ture and People domains.