Towards a Unified Approach to Simultaneous Single-Document and Multi-Document Summarizations

Single-document summarization and multidocument summarization are very closely related tasks and they have been widely investigated independently. This paper examines the mutual influences between the two tasks and proposes a novel unified approach to simultaneous single-document and multidocument summarizations. The mutual influences between the two tasks are incorporated into a graph model and the ranking scores of a sentence for the two tasks can be obtained in a unified ranking process. Experimental results on the benchmark DUC datasets demonstrate the effectiveness of the proposed approach for both single-document and multidocument summarizations.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Xiaojun Wan
• Keywords: COLING 2010, Computational Linguistics, Multidocument Summarizations, Mutual Influences, Unified Ranking Process