Evaluating Layout and Clustering Algorithms for Visualizing Named Entity Graph
Myriad of layout and clustering algorithms exist to generate visual graphs of named entities. Consequently, it is hard for researchers to select the appropriate algorithms that fulfill their needs. This paper intends to assist the researchers by presenting the performance evaluation of the combinat...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universiti Teknikal Malaysia (UTEM)
2017
|
Subjects: | |
Online Access: | http://ir.unimas.my/id/eprint/21711/1/Evaluating%20-%20Copy.pdf http://ir.unimas.my/id/eprint/21711/ http://journal.utem.edu.my/index.php/jtec/article/view/2705 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Malaysia Sarawak |
Language: | English |
Summary: | Myriad of layout and clustering algorithms exist to
generate visual graphs of named entities. Consequently, it is hard for researchers to select the appropriate algorithms that fulfill their needs. This paper intends to assist the researchers by presenting the performance evaluation of the combination of graph layout algorithm followed by a clustering algorithm. The layout algorithms are OpenORD and Hu’s algorithms, and the clustering algorithms are Chinese Whispers and GivanNewman algorithms. The evaluation is carried out on bio-named entities that are linked by some annotated relations. The results of the experimentations highlight the strengths and weaknesses of the four combinations regarding running time, loss of relations (or edges), edge crossing, and cluttered display |
---|