Baldewein et al. 2004b

U. Baldewein and K. Erk and S. Pado and D. Prescher: Semantic Role Labelling With Similarity-Based Generalisation Using EM-based Clustering. Proceedings of SENSEVAL-3, Barcelona.

Note: The results in this paper were obtained from a system which turned out to be somewhat buggy; the judgements about the (limited) usefulness of additional training data should therefore be reconsidered.

We describe a system for semantic role assignment built as part of the Senseval III task, based on an off-the-shelf parser and Maxent and Memory-Based learners. We focus on generalisation using several similarity measures to increase the amount of training data available and on the use of EM-based clustering to improve role assignment. Our final score yields Precision=73.6%, Recall=59.4% (F=65.7).

@InProceedings{baldewein04:_seman_role_label_with_simil,
  author = 	 {U. Baldewein and K. Erk and S. Pado and D. Prescher},
  title = 	 {Semantic Role Labelling With Similarity-Based Generalisation 
                  Using EM-based Clustering},
  booktitle =	 {Proceedings of SENSEVAL-3},
  year =	 2004,
  address =	 {Barcelona}
}

Sebastian Padó