Paper: A Generalized Framework For Revealing Analogous Themese Across Related Topics

ACL ID H05-1123
Title A Generalized Framework For Revealing Analogous Themese Across Related Topics
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors
  • Zvika Marx (Massachusetts Institute of Technology, Cambridge MA)
  • Ido Dagan (Bar Ilan University, Ramat Gan Israel)
  • Eli Shamir (Hebrew University of Jerusalem, Jerusalem Israel)

This work addresses the task of identify- ing thematic correspondences across sub- corpora focused on different topics. We introduce an unsupervised algorithmic framework based on distributional data clustering, which generalizes previous ini- tial works on this task. The empirical re- sults reveal interesting commonalities of different religions. We evaluate the re- sults through measuring the overlap of our clusters with clusters compiled manually by experts. The tested variants of our framework are shown to outperform al- ternative methods applicable to the task.