repository
AUTONOMOUS TEXT SUMMARIZATION USING COLLECTIVE INTELLIGENCE BASED ON NATURE-INSPIRED ALGORITHM
- Author(s)
- KALEAB GETANEH TEFRIE
- Advisor
- Kyung-Ah Sohn
- Department
- 일반대학원 컴퓨터공학과
- Publisher
- The Graduate School, Ajou University
- Publication Year
- 2016-08
- Language
- eng
- Alternative Abstract
- ABSTRACT Thousands of years ago written language was introduced as a way of enhancing and facilitating communication. Fast forward to the twenty first century much has changed, especially the flow of data incrementing at fast rate and we have to use the power of algorithms and hardware technology to understand text more clearly. With the Information age rising we are being cluttered with humongous data each day with no sign of it slowing. humans have been trying to create ways on how to handle this continuous flow of text, image and video. And one of the category of subjects Regarding text is text summarization, given a document coming up with a reasonable summarized version of the original document. people have tried different aspects of summarizing to get a shorter yet an informative definition of document. This paper tries to utilize using nature inspired algorithms to implement an auto summarizer of text using pseudo-selected features. The main objective of this research is to use of cooperative nature-inspired algorithm specifically ant colony algorithm in text mining problems, in our case, text summarization. And throughout the paper we will try to show how this system can be achieved as well as show the performance and effectiveness of the measurement. We have used the standard data used to test summarization techniques, DUC data and at last comparing it to two algorithms for further analysis.
- Fulltext
- Appears in Collections:
- Graduate School of Ajou University > Department of Computer Engineering > 3. Theses(Master)
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
-
- License
- STATISTICS
- Total Visit :3,303,223
- Total Download :1,737
- Today View :11,041
