Combining a double clustering approach with sentence simplification to produce highly informative multi-document summaries

This paper presents a method for extractive multi-document summarization that explores a two-phase clustering approach that, combined with a sentence simplification procedure, aims to generate more useful summaries. First, sentences are clustered by similarity, and one sentence per cluster is selected, to reduce redundancy. Then, in order to group them according to topics, those sentences are clustered considering the collection of keywords. Finally, the summarization process includes a sentence simplification step, which aims not only to create simpler and more incisive sentences, but also to make room for the inclusion of further relevant content in the summary. Evaluation reveals that the approach pursued produces highly informative summaries, containing relevant data and no repeated information.