Learning script participants from unlabeled data

Michaela Regneri, Alexander Koller, Josef Ruppenhofer, and Manfred Pinkal

In Proceedings of the Conference on Recent Advances in Natural Language Processing (RANLP), Hissar, Bulgaria, 2011.

We introduce a system that learns the participants of arbitrary given scripts. This system processes data from web experiments, in which each participant can be realized with different expressions. It computes participants by encoding semantic similarity and global structural information into an Integer Linear Program. An evaluation against a gold standard shows that we significantly outperform two informed baselines.

Download: Download

BibTeX Entry
@InProceedings{participants-11,
	author = {Michaela Regneri and Alexander Koller and Josef
		Ruppenhofer and Manfred Pinkal},
	title = {Learning script participants from unlabeled data},
	booktitle = {Proceedings of the Conference on Recent Advances in
		Natural Language Processing (RANLP)},
	address = {Hissar, Bulgaria},
	year = 2011
}

Back: Publications