Extractive Arabic Text Summarization Using PageRank and Word Embedding

Abstract

Research on graph-based automatic text summarization for Arabic, the official language of 26 nations with over 200 million speakers, as well as other prevalent languages, has recently increased due to the ability of these approaches to handle linguistic peculiarities such as complex morphological linkages. The present paper proposes a graph-based extractive Arabic text summarization (GEATS) technique that employs word embedding and PageRank algorithms for feature extraction and sentence ordering. The efficiency of the GEATS approach versus the state-of-the-art methods is analyzed based on the quality of the produced summaries over the F-measure values. The findings indicated that it outperformed the nearest alternative by an advantage of over 7.5%.