Background | Entailment learning Two information types have primarily been utilized to learn entailment rules between predicates: lexicographic resources and distributional similarity resources. |
Background | Therefore, distributional similarity is used to learn broad-scale resources. |
Background | Distributional similarity algorithms predict a semantic relation between two predicates by comparing the arguments with which they occur. |
Experimental Evaluation | When computing distributional similarity scores, a template is represented as a feature vector of the CUIs that instantiate its arguments. |
Experimental Evaluation | Local algorithms We described 12 distributional similarity measures computed over our corpus (Section 5.1). |
Experimental Evaluation | For each distributional similarity measure (altogether 16 measures), we learned a graph by inserting any edge (u, v) , when u is in the top K templates most similar to 2). |
Learning Entailment Graph Edges | Next, we represent each pair of propositional templates with a feature vector of various distributional similarity scores. |
Learning Entailment Graph Edges | Distributional similarity representation We aim to train a classifier that for an input template pair (t1, t2) determines whether t1 entails 752. |
Learning Entailment Graph Edges | A template pair is represented by a feature vector where each coordinate is a different distributional similarity score. |
Set Expansion | We consider three similarity data sources: the Moby thesaurus1 , WordNet (Fellbaum, 1998), and distributional similarity based on a large corpus of text (Lin, 1998). |
Set Expansion | Distributional similarity . |
Set Expansion | Second, the data sources used: each source separately (M for Moby, W for WordNet, D for distributional similarity ), and all three in combination (MWD). |