Cross-partition clustering: revealing corresponding themes across related datasets

• Published in: Journal of experimental & theoretical artificial intelligence Vol. 23; no. 2; pp. 153 - 180
• Main Authors: Marx, Zvika, Dagan, Ido, Shamir, Eli
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis Group 01.06.2011; Taylor & Francis Ltd
• Subjects: analogy; Artificial intelligence; Cluster analysis; Collection; Commonality; data clustering; Empirical analysis; Expert systems; information theory; natural language processing; Objectives; Religion; structure mapping; Tasks; text mining; Texts

This article studies the task of discovering correspondences across related domains based on real-world data collections. We address this task through a designated extension of distributional data-clustering methods. The method is empirically demonstrated on synthetic data as well as on texts addres...