Multi-document Text Summarization Based on Genetic Algorithm and the Relevance of Sentence Features

Document Text Summarization aims to create a short and condensed version from the original document, which transmits the main idea of the document in a few words. We formulated extractive multi-document text summarization as a combinatorial optimization problem. In which we used sentence features to select the most important content. We conduct experiments on Document Understanding Conference (DUC01) dataset using the ROUGE toolkit. Our experiments demonstrate that the proposed method contributes significant improvements over the state-of-the-art methods and heuristics.