Abstract / Description of output
We present the psycholinguistically motivated task of predicting human plausibility judgements for verb-role-argument triples and introduce a probabilistic model that solves it. We also evaluate our model on the related role-labelling task, and compare it with a standard role labeller. For both tasks, our model benets from classbased smoothing, which allows it to make correct argument-specic predictions despite a severe sparse data problem. The standard labeller suffers from sparse data and a strong reliance on syntactic cues, especially in the prediction task.
| Original language | English |
|---|---|
| Title of host publication | EACL 2006, 11st Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, April 3-7, 2006, Trento, Italy |
| Pages | 1-8 |
| Number of pages | 8 |
| Publication status | Published - 2006 |