The Learnability of Description Logics with Equality Constraints
Machine Learning - Special issue on computational learning theory, COLT'92
Fast Algorithms for Mining Association Rules in Large Databases
VLDB '94 Proceedings of the 20th International Conference on Very Large Data Bases
Discovery of Maximal Analogies between Stories
DS '02 Proceedings of the 5th International Conference on Discovery Science
KeyGraph: Automatic Indexing by Co-occurrence Graph based on Building Construction Metaphor
ADL '98 Proceedings of the Advances in Digital Libraries Conference
Japanese dependency analysis using cascaded chunking
COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
Hi-index | 0.00 |
In order to construct story databases, it is crucial to have an effective index that represents the plot and event sequences in a document. For this purpose, we have already proposed a method using the concept of maximal analogy to represent a generalized event sequence of documents with a maximal set of events. However, it is expensive to calculate a maximal analogy from documents with a large number of sentences. Therefore, in this paper, we propose an efficient algorithm to generate a maximal analogy, based on graph theory, and we confirm its effectiveness experimentally. We also discuss how to use a maximal analogy as an index for a story database, and outline our future plans.