Sentence Reduction Algorithms to Improve Multi-document Summarization

Multi-document summarization aims to create a single summary based on the information conveyed by a collection of texts. After the candidate sentences have been identified and ordered, it is time to select which will be included in the summary. In this paper, we describe an approach that uses sentence reduction, both lexical and syntactic, to help improve the compression step in the summarization process. Three different algorithms are proposed and discussed. Sentence reduction is performed by removing specific sentential constructions conveying information that can be considered to be less relevant to the general message of the summary. Thus, the rationale is that sentence reduction not only removes expendable information, but also makes room for further relevant data in a summary.