Sentence selection methods for text summarization

Abstract

Güran, Aysun (Dogus Author) -- Conference full title: 2014 22nd Signal Processing and Communications Applications Conference (SIU) = 2014 22. Sinyal İşleme ve İletişim Uygulamaları Kurultayı (SİU): 23-25 April 2014, Trabzon, Turkey.Bu çalışmanın amacı, bir dokümandaki en önemli cümleleri seçerek ilgili dokümanın özetini çıkarmaktır. Bu amaçla 15 farklı cümle seçim metodu kullanılmıştır. Bu metotlar, 15 kadın ve 15 erkek olmak üzere, toplam 30 kişi tarafından çıkarılmış özet dokümanlarının oluşturduğu bir değerlendirme veri seti üzerinde kıyaslanmıştır. Ayrıca, bu metotlardan en başarılı olanlarının birlikte kullanılması ile elde edilen farklı özellik gruplarının başarım değerleri sergilenmiş ve analiz sonuçları paylaşılmıştır.The aim of this work is to create text summaries by selecting the most important sentences of documents. For this aim 15 sentence selection methods are used. These methods are compared on the evaluation set created by 15 women and 15 men evaluators. The performance results of the systems that are obtained by using different sentence selecetion methods together are also analyzed and the results are shared

A New Model on Automatic Text Summarization for Turkish

“…Two datasets, namely Dataset I and Dataset II [1,10], were used in Turkish news on the economy, sports, and art categories to investigate the contribution of eight different features to the success of text summarization. The documents in Datasets I and II were summarized by 5 and 30 different assessors, respectively.…”

“…The value of this feature for a given sentence corresponds to the number of nouns in the sentence [1]. The nouns are detected using the Zemberek library [13].…”

“…where k defines the ratio of sentences used in the summary and defined to be 0.35 as indicated in [1].…”

“…Text summarization is the task of attaining a shorter version of one document or multiple documents in which the same main idea and prominent information are covered. If the summarization of a text is carried out by a computer, it is called automatic text summarization [1]. Nowadays, it is tough to acquire the brief data we want to obtain in the informational convergence.…”

“…The first dataset consists of 100 texts in the categories of economy, arts, and sports. The second dataset [1,10] consists of 20 texts in various categories: economy, art, health, and sports. The third dataset was produced by combining these two datasets.…”