Document summarization using positive pointwise mutual information

TL;DR

This paper introduces a novel document summarization method that leverages positive pointwise mutual information to weight term-sentence matrices, improving the extraction of significant sentences for better summaries.

Contribution

The paper proposes a new summarization technique using positive pointwise mutual information for semantic similarity measurement, outperforming existing methods on large documents.

Findings

Outperforms most existing summarization methods

Effective in handling large documents

Uses semantic similarity for better sentence selection

Abstract

The degree of success in document summarization processes depends on the performance of the method used in identifying significant sentences in the documents. The collection of unique words characterizes the major signature of the document, and forms the basis for Term-Sentence-Matrix (TSM). The Positive Pointwise Mutual Information, which works well for measuring semantic similarity in the Term-Sentence-Matrix, is used in our method to assign weights for each entry in the Term-Sentence-Matrix. The Sentence-Rank-Matrix generated from this weighted TSM, is then used to extract a summary from the document. Our experiments show that such a method would outperform most of the existing methods in producing summaries from large documents.