Firefly Algorithm Based Multilingual Named Entity Recognition for Indian Languages

Abstract

Named Entity Recognition (NER) is considered as a very influential undertaking in natural language processing appropriate to Question Answering system, Machine Translation (MT), Information extraction (IE), Information Retrieval (IR) etc. Basically NER is to identify and classify different types of proper nouns present inside given filelike location name, person name, number, organization name, time etc. Multilingual NER is a task where NE can be recognized for variety of Languages by implementing one or more methods. In this paper, we have implemented Conditional Random Field (CRF) as a base and firefly Algorithm (FA) to effectively combine different feature representation. For better performance of this system, we have combined both the methods. We have taken three Indian languages Hindi, Bengali, and Odiya for the purpose of evaluation. A promising result is observed for all three languages while implementing FA with CRF.