The Potsdam NLG systems at the GIVE-2.5 Challenge

Konstantina Garoufi and Alexander Koller

In GIVE-2.5 Challenge: System descriptions, Nancy, 2011.

We present the Potsdam natural language generation systems P1 and P2 of the GIVE-2.5 Challenge. The systems implement two different referring expression generation models from Garoufi and Koller (2011) while behaving identically in all other respects. In particular, P1 combines symbolic and corpus-based methods for the generation of successful referring expressions, while P2 is based on a purely symbolic model which serves as a qualified baseline for comparison. We describe how the systems operated in the challenge and discuss the results, which indicate that P1 outperforms P2 in terms of several measures of referring expression success.

Download: Download

BibTeX Entry
@InProceedings{give25-potsdam,
	author = {Konstantina Garoufi and Alexander Koller},
	title = {{The Potsdam NLG systems at the GIVE-2.5 Challenge}},
	booktitle = {GIVE-2.5 Challenge: System descriptions},
	address = {Nancy},
	year = 2011
}

Back: Publications