SUMMA: A Robust and Adaptable Summarization Tool

Horacio Saggion*
*Department of Computer Science; University of Sheffield; 211 Portobello Street; Sheffield, England, UK;
Résumé (en anglais)
Over the last few years there has been substantial research on text summarization, but comparatively little research has been carried out on adaptable components that allow rapid development and evaluation of summarization solutions. This paper presents a set of adaptable summarization components together with well-established evaluation tools, all within the GATE paradigm. The toolkit includes resources for the computation of summarization features which are combined in order to provide functionalities for single-document, multi-document, query-based, and multi/cross-lingual summarization. The summarization tools have been successfully used in a number of applications including a fully-fledged information access system.