Learning Script Participants from Unlabeled Data

@inproceedings{Regneri2011LearningSP,
  title={Learning Script Participants from Unlabeled Data},
  author={Michaela Regneri and Alexander Koller and Josef Ruppenhofer and Manfred Pinkal},
  booktitle={RANLP},
  year={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. 
Highly Cited
This paper has 19 citations. REVIEW CITATIONS
14 Citations
29 References
Similar Papers

Similar Papers

Loading similar papers…