Chronological Ordering Based on Context Overlap Detection

Chronological Ordering Based on Context Overlap Detection

Mohamed H. Haggag (Department of Computer Science, Faculty of Computers & Informantion, Helwan University, Cairo, Egypt) and Bassma M. Othman (Department of Computer Science, Faculty of Computers & Informantion, Helwan University, Cairo, Egypt)
Copyright: © 2012 |Pages: 14
DOI: 10.4018/ijirr.2012100103
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Context processing plays an important role in different Natural Language Processing applications. Sentence ordering is one of critical tasks in text generation. Following the same order of sentences in the row sources of text is not necessarily to be applied for the resulted text. Accordingly, a need for chronological sentence ordering is of high importance in this regard. Some researches followed linguistic syntactic analysis and others used statistical approaches. This paper proposes a new model for sentence ordering based on sematic analysis. Word level semantics forms a seed to sentence level sematic relations. The model introduces a clustering technique based on sentences senses relatedness. Following to this, sentences are chronologically ordered through two main steps; overlap detection and chronological cause-effect rules. Overlap detection drills down into each cluster to step through its sentences in chronological sequence. Cause-effect rules forms the linguistic knowledge controlling sentences relations. Evaluation of the proposed algorithm showed the capability of the proposed model to process size free texts, non-domain specific and open to extend the cause-effect rules for specific ordering needs.
Article Preview

The goal is to determine a most probable replacement of sentences or, in other words, reconstruct speak structure of sentences gathered from multiple sources. When a human is asked to make an arrangement of sentences, he or she may perform this task without difficulty just as writing out thoughts in a text. However, they considered what accomplishes this task since computers are unaware of order of things by nature. There are many searches in ordering sentences techniques. Tiedan Zhu et al. (2012) presented an improved approach to sentence ordering in multi document summarization. They rely on using sentences logical closeness by defining the notation a→b to represent that a and b are adjacent. The ‘adjacent’ here means: a and b are coherent enough to be connected together in a document (summary); second, a precedes b. then they defined the sentence-chain which is a chain of adjacent sentences, i.e. A = (a1→a2→…→an-1→an) is a sentence-chain with the length of n, where ai is a sentence. Then Used the arrow with sentence-chains, A→B= (a1→a2→…→an-1→an→b1→b2→…→bm-1→bm). The result of two sentence-chains connected with an arrow is still a sentence-chain.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 8: 4 Issues (2018): 1 Released, 3 Forthcoming
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing