Graph based KNN for Text Summarization
- Authors
- Jo, Taeho
- Issue Date
- 2018
- Publisher
- IEEE
- Keywords
- Text Summarization; Graph Similarity; Graph based KNN
- Citation
- 2018 20TH INTERNATIONAL CONFERENCE ON ADVANCED COMMUNICATION TECHNOLOGY (ICACT), pp.438 - 443
- Journal Title
- 2018 20TH INTERNATIONAL CONFERENCE ON ADVANCED COMMUNICATION TECHNOLOGY (ICACT)
- Start Page
- 438
- End Page
- 443
- URI
- https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/28141
- ISSN
- 1738-9445
- Abstract
- In this research, we propose that the graph based KNN (K Nearest Neighbor) should be applied to the text summarization tasks. The text summarization tasks may be interpreted into the binary classification tasks, and sentences or paragraphs may be encoded into graphs as well as articles. In this research, we encode sentences or paragraphs into graphs under the view of the text summarization tasks into the task where they are classified into essential parts, or not, modify the KNN into the graph based version where each graph is given as its input data, and apply it to the classification task which is mapped from the text summarization. As the benefits from this research, we expect the more compact, graphical, and symbolic representations of sentences or paragraphs and the improved text summarization performance. Therefore, the goal of this research is to implement the text summarization system with its improved performance and representations of data items.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - School of Games > Game Software Major > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/28141)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.