Gon Kim , Jae Gun Yang , Jae Hak J. Bae , Jong Hyeok Lee

The KIPS Transactions:PartB , Vol. 11, No. 5, pp. 563-572, Aug. 2004
10.3745/KIPSTB.2004.11.5.563,   PDF Download:

Abstract

Sentence abstraction is a simplification of a sentence preserving its communicative function. It accomplishes sentence revision and concept abstraction simultaneously. Sentence revision is a method that resolves the discrepancy between human's thoughts and its expressed semantic in sentences. Concept abstraction is an expression of general ideas acquired from the common elements of concepts. Sentence abstraction selects the main constituents of given sentences and describes the upper concepts of them with detecting their semantic information. This enables sentence revision and concept abstraction simultaneously. In this paper, a syntactic parser LGPI and an ontology OfN are utilized for sentence abstraction. Sentence abstracter SABOT makes use of LGPI and OfN. SABOT processes the result of parsing and selects the candidate words for sentence abstraction. This paper computes the sentence recall of the main sentences and the topic hit ratio of the selected sentences with the text understanding system using sentence abstraction. The sources are 58 paragraphs in 23 stories. As a result of it, the sentence recall is about 54~72% and the topic hit ratio is about 76~86% This paper verified that sentence abstraction enables sentence revision that can select the topic sentences of a given text efficiently and concept abstraction that can improve the depth of text understanding.

Statistics
Cite this article