Research on the Term Relation Identification Based on Fuzzy Comprehension Evaluation Method -- A Case Study on the Natural Disaster Risk Term

DOI

10.2991/ifmca-16.2017.16How to use a DOI?

Keywords

Fuzzy comprehension evaluation; term relation identification; similarity; natural disaster risk term

Abstract

Based on the existing terminology in the Chinese science & technology term system of natural disaster monitoring and defense, in this article, fuzzy identification of term relation is conducted by multi-strategy fuzzy comprehension evaluation. First, calculate similarity through various similarity computing methods; then determine division of relation category and threshold range through continuous attributes discretization method, and determine factor weight through particle swarm algorithm and cross validation method; and finally, integrate and process computed results of all similarity computing methods through fuzzy comprehension evaluation method, so as to achieve fuzzy identification of term relation. Evaluate the results of relation identification via precision, recall and F value, to demonstrate effectiveness of this method. By using the existing terms in natural disaster risk monitoring scientific and technical word system as a test set, it is found that the method can effectively realize the recognition of terms.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hui Li
AU  - Jing Zhang
AU  - Xiaohong Jin
AU  - Yunliang Zhang
PY  - 2017/03
DA  - 2017/03
TI  - Research on the Term Relation Identification Based on Fuzzy Comprehension Evaluation Method -- A Case Study on the Natural Disaster Risk Term
BT  - Proceedings of the 2016 International Forum on Mechanical, Control and Automation (IFMCA 2016)
PB  - Atlantis Press
SP  - 104
EP  - 113
SN  - 2352-5401
UR  - https://doi.org/10.2991/ifmca-16.2017.16
DO  - 10.2991/ifmca-16.2017.16
ID  - Li2017/03
ER  -