| Experiments | and Matsumoto, 2003) to convert the phrase structure syntax of the Treebank into a dependency tree representation, dependency labels were obtained via the ”Malt” hard-coded setting.8 We split the Treebank into a training set (Sections 2-2l), a development set (Section 22), and several test sets (Sections 0,9 l, 23, and 24). |
| Web-Derived Selectional Preference Features | Figure 2: An example of a labeled dependency tree . |
| Web-Derived Selectional Preference Features | In this paper we generalize the adjacency and dependency models by including the pointwise mutual information (Church and Hanks, 1900) between all pairs of words in the dependency tree: |
| Web-Derived Selectional Preference Features | tween the three words in the dependency tree: |