Extractive Text Summarization Based on Selectivity Ranking (CROSBI ID 707858)
Prilog sa skupa u zborniku | ostalo | međunarodna recenzija
Podaci o odgovornosti
Aljević, Dino ; Todorovski, Ljupčo ; Martinčić-Ipšić, Sanda
engleski
Extractive Text Summarization Based on Selectivity Ranking
Extractive summarization of text documents deals with automatic creation of a summary by combining the most salient sentences extracted from the original text document into a more concise form. In this paper, we introduce a novel graphbased method for extractive summarization that transforms a given text into a graph of interconnected sentences and employs computationally efficient selectivity measure to measure the importance of graph nodes. In turn, the text summary is build upon the sentences corresponding to the most important graph nodes. The edges in the graph are based on three measures of similarity between sentences, i.e., Mihalcea’s, Jaccard and Cosine. The first among the three leads to best performance, which also compares favorably to the performance of three alternative summarization methods of TF-IDF, centroid and TextRank. The results confirm that selectivity of nodes in a text graph build using the Mihalcea’s similarity between sentences is a computationally efficient and well performing method for extractive summarization
natural language processing, extractive summarization, graph-based method, selectivity measure
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1-6.
2021.
objavljeno
10.1109/INISTA52262.2021.9548408
Podaci o matičnoj publikaciji
2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)
Lahti: IEEE INISTA
978-1-6654-3602-1
Podaci o skupu
2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)
predavanje
25.08.2021-27.08.2021
Kocaeli, Turska