Part-of-speech tagging using genetic algorithms

被引：0

作者：

Department of Computer Science and Engineering, Lovely Professional University, Jalandhar ^{[1
]}

Punjab, India

机构：

[1] Department of Computer Science and Engineering, Lovely Professional University, Jalandhar, Punjab

来源：

Int. J. Simul. Syst. Sci. Technol. | / 6卷 / 11.1-11.7期

关键词：

Genetic algorithm; Natural language processing; Part of speech; Punjabi;

D O I：

10.5013/IJSSST.a.16.06.11

中图分类号：

学科分类号：

摘要：

To the best of our knowledge genetic algorithms have never been used for prediction of POS tags for Punjabi Language. In this paper, A classic Genetic Algorithm (GA) with fixed gene length is proposed for sentence-level Punjabi language tagging. It uses fixed individual size, value type encoding, Roulette wheel selection, adaptive - two point crossover (TPC) and varying mutation rate as operators in proposed work. Focusing on the relationship of tags according to context, we are proposing this technique in form of a software prototype and an algorithm. A dataset of 26,000 hand tagged words is used for proposed work and 90.63% accuracy is achieved. © 2015, UK Simulation Society. All rights reserved.

引用

页码：11.1 / 11.7