Coherent Arrangement of Sentences Extracted from Multiple Newspaper Articles

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.

• Type: Conference
• Year: 2004
• Where: PRICAI
• Authors: Naoaki Okazaki, Yutaka Matsuo, Mitsuru Ishizuka
• Keywords: Artificial Intelligence, Important Sentence Extraction, Most Multi-document Summarization, Multi-document Summarization, PRICAI 2004