Background | Most work on learning entailment rules between predicates considered each rule independently of others, using two sources of information: lexicographic resources and distributional similarity . |
Background | Distributional similarity algorithms use large corpora to learn broader resources by assuming that semantically similar predicates appear with similar arguments. |
Background | Distributional similarity algorithms differ in their feature representation: Some use a binary representation: each predicate is represented by one feature vector where each feature is a pair of arguments (Szpektor et al., 2004; Yates and Etzioni, 2009). |
Experimental Evaluation | Second, to distributional similarity algorithms: (a) SR: the score used by Schoenmackers et al. |
Experimental Evaluation | Third, we compared to the entailment classifier with no transitivity constraints (clsf) to see if combining distributional similarity scores improves performance over single measures. |
Learning Typed Entailment Graphs | We compute 11 distributional similarity scores for each pair of predicates based on the arguments appearing in the extracted arguments. |
Abstract | Finally, we present a ranker that employs distributional similarities to build a network of words, and captures the diversity of perspectives by detecting communities in this network. |
Conclusion and Future Work | Finally, we proposed a ranking system that employs word distributional similarities to identify semantically equivalent words, and compared it with a wide |
Diversity-based Ranking | 5.1 Distributional Similarity |
Diversity-based Ranking | In order to capture the nuggets of equivalent semantic classes, we use a distributional similarity of |
Diversity-based Ranking | The method based on the distributional similarities of words outperforms other methods in the citations category. |