Annotating the argument structure of deverbal nominalizations in Spanish
Language Resources and Evaluation
Empirical methods for the study of denotation in nominalizations in spanish
Computational Linguistics
| Hi-index | 0.00 |
We describe an experiment mapping semantic role preferences for transitive verbs to their deverbal nominal forms. The preferences are learned by data mining large parsed corpora. Preferences are modeled for deverbal/argument pairs, falling back to a model for the deverbal alone when sufficient data is not available. Errors in role assignment are reduced by 35%.