Contrastive Summarization

With the continual growth of the internet as a source of information, where a great amount of data is being uploaded every minute, the need for data compression is getting more important. This applies also to textual documents. As the amount of data grows, the probability of multiple similar documents is increasing. One way how to deal with this is to reduce the text, i.e. to use document summarization. In this work, we focus on a specific task – contrastive summarization. The aim is to compare two sets of textual documents in order to obtain latent topics discussed there, as well as the opinions of authors, and create a summary depicting the main topics and opinions mentioned there. The first two chapters of this work describe the basic terms and problems of summarization. The third and fourth chapter sum up the existing methods in comparative and contrastive summarization respectively. The last chapter describes our future plans and our proposal of a novel method for contrastive summarization. Copies of this report are available on http://www.kiv.zcu.cz/en/research/publications/ or by surface mail on request sent to the following address: University of West Bohemia in Pilsen Department of Computer Science and Engineering Univerzitni 8 30614 Pilsen Czech Republic Copyright © 2013 University of West Bohemia in Pilsen, Czech Republic Contrastive Summarization PhD Thesis Proposal Author: Ing. Michal Campr Supervisor: Prof. Ing. Karel Ježek CSc. 28. July 2013