Skip to Main Content
In this paper, a novel summarization method, which uses non-negative matrix factorization (NMF) and NMF clustering, is introduced to extract meaningful sentences from query-based multi-documents. The proposed method decomposes a sentence into the linear combination of sparse non-negative semantic features so that it can represent a sentence as the sum of a few semantic features that are comprehensible intuitively. It can improve the quality of document summaries because it can avoid extracting the sentences whose similarities with query are high but are meaningless by using the similarity between the query and the semantic features. Besides, it uses NMF clustering to remove noises so that it can avoid the biased inherent semantics of the documents to be reflected in summaries. Also it can ensure the coherence of summaries by using the rank score of sentences with respect to semantic features. The experimental results demonstrate that the proposed method has better performance than other methods using the thesaurus, the LSA, the K-means, and the NMF.