Multi-Document Summarization Model Based on Integer Linear Programming

Abstract

This paper proposes an extractive generic text summarization model that generates summaries by selecting sentences according to their scores. Sentence scores are calculated using their extensive coverage of the main content of the text, and summaries are created by extracting the highest scored sentences from the original document. The model formalized as a multiobjective integer programming problem. An advantage of this model is that it can cover the main content of source (s) and provide less redundancy in the generated summaries. To extract sentences which form a summary with an extensive coverage of the main content of the text and less redundancy, have been used the similarity of sentences to the original document and the similarity between sentences. Performance evaluation is conducted by comparing summarization outputs with manual summaries of DUC2004 dataset. Experiments showed that the proposed approach outperforms the related methods.

Text-Image-Video Summary Generation Using Joint Integer Linear Programming

“…Various techniques like graph-based methods [6,15,16], artificial neural networks [22] and deep learning based approaches [18,20,29] have been developed for text summarization. Integer linear programming (ILP) has also shown promising results in extractive document summarization [1,9]. Duan et al [5] proposed a joint-ILP framework that produces summaries from temporally separate text documents.…”

An Optimization Approach to Automatic Generic Document Summarization

“…In this paper, the objective functions we defined as a weighted linear combination and a weighted harmonic mean of the coverage and redundancy objectives. We note that these combinations, with tuning of the weighting parameters, allow getting the best summary. In Alguliev et al (2010), content coverage of each sentence is defined by its similarity to the center of sentence collection and in Aguliev et al (2011) it is defined by the similarity of sentence to the whole document collection. It is known (Aliguliyev, 2010) that the similarity measure plays an important role in text summarization.…”

“…Here a weighting parameter specifies the relative contributions to the final information richness of sentences from the cosine and the NGD‐based measures. In this study, the content coverage of each sentence is defined by the sum of its similarity to the other sentences in collection. In Alguliev et al (2010) to solve the integer linear programming problem the GNU Linear Programming kit is used, which is a free optimization package (http://www.gnu.org/software/glpk/). In Alguliev et al (2011), the optimization problem is solved using PSO‐LDW (PSO with linearly decreasing inertia weight) algorithm.…”

“…In Alguliev et al (2010), content coverage of each sentence is defined by its similarity to the center of sentence collection and in Aguliev et al (2011) it is defined by the similarity of sentence to the whole document collection. It is known (Aliguliyev, 2010) that the similarity measure plays an important role in text summarization.…”

“…In Alguliev et al (2010) to solve the integer linear programming problem the GNU Linear Programming kit is used, which is a free optimization package (http://www.gnu.org/software/glpk/). In Alguliev et al (2011), the optimization problem is solved using PSO‐LDW (PSO with linearly decreasing inertia weight) algorithm.…”