Mining both Commonality and Specificity from Multiple Documents for Multi-Document Summarization
This addresses the problem of generating summaries that balance coverage and diversity for users in text summarization, though it appears incremental as it builds on existing clustering techniques.
The paper tackles multi-document summarization by proposing an approach that mines both commonality and specificity from documents using hierarchical clustering, achieving competitive performance on DUC'2004 and Multi-News datasets compared to state-of-the-art methods.
The multi-document summarization task requires the designed summarizer to generate a short text that covers the important information of original documents and satisfies content diversity. This paper proposes a multi-document summarization approach based on hierarchical clustering of documents. It utilizes the constructed class tree of documents to extract both the sentences reflecting the commonality of all documents and the sentences reflecting the specificity of some subclasses of these documents for generating a summary, so as to satisfy the coverage and diversity requirements of multi-document summarization. Comparative experiments with different variant approaches on DUC'2002-2004 datasets prove the effectiveness of mining both the commonality and specificity of documents for multi-document summarization. Experiments on DUC'2004 and Multi-News datasets show that our approach achieves competitive performance compared to the state-of-the-art unsupervised and supervised approaches.