COMPENDIUM: A text summarization system for generating abstracts of research papers

Abstract

This paper presents COMPENDIUM, a text summarization system, which has achieved good results in extractive summarization. Therefore, our main goal in this research is to extend it, suggesting a new approach for generating abstractive-oriented summaries of research papers. We conduct a preliminary analysis where we compare the extractive version of COMPENDIUM (COMPENDIUM E) with the new abstractive-oriented approach (COMPENDIUM E-A). The final summaries are evaluated according to three criteria (content, topic, and user satisfaction) and, from the results obtained, we can conclude that the use of compendium is appropriate for producing summaries of research papers automatically, going beyond the simple selection of sentences. © 2011 Springer-Verlag.