Academic Journals Database
Disseminating quality controlled scientific knowledge

GENETIC ALGORITHM (GA) IN FEATURE SELECTION FOR CRF BASED MANIPURI MULTIWORD EXPRESSION (MWE) IDENTIFICATION

ADD TO MY LIST
 
Author(s): Kishorjit Nongmeikapam | Sivaji Bandyopadhyay

Journal: International Journal of Computer Science & Information Technology
ISSN 0975-4660

Volume: 3;
Issue: 5;
Start page: 53;
Date: 2011;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: CRF | MWE | Manipuri | GA | Features

ABSTRACT
This paper deals with the identification of Multiword Expressions (MWEs) in Manipuri, a highlyagglutinative Indian Language. Manipuri is listed in the Eight Schedule of Indian Constitution. MWEplays an important role in the applications of Natural Language Processing(NLP) like MachineTranslation, Part of Speech tagging, Information Retrieval, Question Answering etc. Feature selection isan important factor in the recognition of Manipuri MWEs using Conditional Random Field (CRF). Thedisadvantage of manual selection and choosing of the appropriate features for running CRF motivates usto think of Genetic Algorithm (GA). Using GA we are able to find the optimal features to run the CRF.We have tried with fifty generations in feature selection along with three fold cross validation as fitnessfunction. This model demonstrated the Recall (R) of 64.08%, Precision (P) of 86.84% and F-measure (F)of 73.74%, showing an improvement over the CRF based Manipuri MWE identification without GAapplication.
Affiliate Program      Why do you need a reservation system?