DocumentCode :
120279
Title :
Information Extraction of Strategic Activities Based on Semi-structured Text
Author :
Xubu Ma ; Guo, Ju E.
Author_Institution :
Sch. of Manage., Xi´an jiaotong Univ., Xi´an, China
fYear :
2014
fDate :
4-6 July 2014
Firstpage :
579
Lastpage :
583
Abstract :
The paper constructed the information extraction method to extract description characteristic of execution process from the description text to provide data support for the evaluation of enterprise strategy execution effectiveness. The constructed information extraction method included two stages, i.e., Feature information extraction and information integration. It overcame some weaknesses of the current information extraction technology, such as its mere use for extracting time, address and other named entities. Firstly, the information extraction process of descriptive information is designed through establishing substantial GATE vocabularies and compiling ordinary and special extraction rules to avoid the disadvantages of the identification of GATE in Chinese named entity. Then, rules of integration of description characteristics information are established on the basis of semantic relation, positional relation to structurally represent the process of executing strategic activities.
Keywords :
information retrieval; learning (artificial intelligence); text analysis; Chinese named entity; GATE vocabulary; description text; descriptive information; enterprise strategy execution effectiveness; extraction rules; feature information extraction; information extraction method; information integration; positional relation; semantic relation; semistructured text; strategic activity; Authorization; Data mining; Educational institutions; Feature extraction; Information retrieval; Logic gates; Psychology; information extraction; information integration; semi-structured text;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Sciences and Optimization (CSO), 2014 Seventh International Joint Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-5371-4
Type :
conf
DOI :
10.1109/CSO.2014.114
Filename :
6923752
Link To Document :
بازگشت