Named Entity Recognition in Indian Languages Using Gazetteer Method and Hidden Markov Model: A Hybrid Approach
Journal Title: International Journal of Computer Science & Engineering Technology - Year 2012, Vol 3, Issue 12
Abstract
Named Entity Recognition (NER) is the task of processing text to identify and classify names, which is an important component in many Natural Language Processing (NLP) applications, enabling the extraction of useful information from documents. Basically NER is a two step process and used for many application like Machine Translation. Indian languages are free order, and highly inflectional and morphologically rich in nature. In this paper we describe the various approaches used for NER and summery on existing work done in different Indian Languages (ILs) using different approaches and also describe brief introduction about Hidden Markov Model And the Gazetteer method for NER. We also present some experimental result using Gazetteer method and HMM method that is a hybrid approach. Finally in the last the paper also describes the comparison between these two methods separately and then we combine these two methods so that performance of the system is increased.
Authors and Affiliations
Nusrat Jahan , Sudha Morwal , Deepti Chopra
Keywords
Related Articles
- EP ID EP114585
- DOI -
- Views 109
- Downloads 0
Survey on Data Sharing In the Cloud Using Distributed Accountability
In cloud computing, resources are share among multiple clients and it is important for cloud service provider to allocate these resources for such clients. Cloud computing is an infrastructure that provides on demand net...
A Multi-hop approach for sensing coverage in wireless sensor network
Wireless sensor networks (WSNs) are recently rapidly growing research area in wireless communications. WSNs are studied widely and usefully applied in many applications like military surveillance, environmental monitorin...
Power-Time Efficient Algorithm for Computing Reconfigurable FFT in Wireless Sensor Network
Wireless sensor network have several constraints, such as a short transmission range, poor processing capabilities, limited available power and slow execution time. The design of algorithms for fast processing of informa...
Remote Based Security System
Background Subtraction is one of the vital image handling steps for video surveillance and many computer vision difficulties such as recognition, classification, activity investigation &tracking. Detection of moving...
Forming Packages of the Services as a Way for Keeping Existing Users and for Increasing ARPU
One company can sells two or more separate products in a package for a single price. It is called „bundling“. In this paper is described bundling in telecommunications area, that is, forming packages of the services, lik...