Multi-document summarization is a challenge to information overload problem to provide a condensed text for a number of documents. Most multi-document summarization systems make use of extraction techniques (e.g., important sentence extraction) and compile a summary from the selected information. However, sentences gathered from multiple sources are not organized as a comprehensible text. Therefore, it is important to consider sentence ordering of extracted sentences in order to reconstruct discourse structure in a summary. We propose a novel method to plan a coherent arrangement of sentences extracted from multiple newspaper articles. Results of our experiment show that sentence reordering has a discernible effect on summary readability. The results also shows significant improvement on sentence arrangement compared to former methods. © Springer-Verlag Berlin Heidelberg 2004.
CITATION STYLE
Okazaki, N., Matsuo, Y., & Ishizuka, M. (2004). Coherent arrangement of sentences extracted from multiple newspaper articles. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3157, pp. 882–891). Springer Verlag. https://doi.org/10.1007/978-3-540-28633-2_93
Mendeley helps you to discover research relevant for your work.