Named Entity Recognition System for Postpositional Languages: Urdu as a Case Study
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2016, Vol 7, Issue 10
Abstract
Named Entity Recognition and Classification is the process of identifying named entities and classifying them into one of the classes like person name, organization name, location name, etc. In this paper, we propose a tagging scheme Begin Inside Last -2 (BIL2) for the Subject Object Verb (SOV) languages that contain postposition. We use the Urdu language as a case study. We compare the F-measure values obtained for the tagging schemes IO, BIO2, BILOU and BIL2 using Hidden Markov Model (HMM) and Conditional Random Field (CRF). The BIL2 tagging scheme results are better than the other three tagging schemes using the same parameters including bigram and context window. With HMM, the F-measure values for IO, BIO2, BILOU, and BIL2 are 44.87%, 44.88%, 45.14%, and 45.88%, respectively. With CRF, the F-measure values for IO, BIO2, BILOU, and BIL2 are 35.13%, 35.90%, 37.85%, and 38.39%, respectively. The F-measure values for BIL2 are better than those of previously reported techniques
Authors and Affiliations
Muhammad Malik, Syed Sarwar
Keywords
Related Articles
- EP ID EP107327
- DOI 10.14569/IJACSA.2016.071019
- Views 113
- Downloads 0
Energy Management Strategy of a PV/Fuel Cell/Supercapacitor Hybrid Source Feeding an off-Grid Pumping Station
This work aims to develop an accurate energy management strategy for a hybrid renewable energy system feeding a pumping station. A developed model under Simulink environment is used to compare the performance of the pump...
PSIM and MATLAB Co-Simulation of Photovoltaic System using “P and O” and “Incremental Conductance” MPPT
The photovoltaic (PV) generator shows a nonlinear current-voltage (I-V) characteristic that its maximum power point (MPP) differs with irradiance and temperature. by employing simple maximum power point tracking algorith...
Reconstruction of Fingerprint Shape using Fractal Interpolation
One of the severe problems in a fingerprint-based system is retaining the fingerprint images. In this paper, we propose a method to minimize the fingerprint images size and retain the reference points. The method is divi...
A Comparison of Sentiment Analysis Methods on Amazon Reviews of Mobile Phones
The consumer reviews serve as feedback for busi-nesses in terms of performance, product quality, and consumer service. In this research, we predict consumer opinion based on mobile phone reviews, in addition to providing...
Holistic Evaluation Framework for Automated Bug Triage Systems: Integration of Developer Performance
Bug Triage is an important aspect of Open Source Software Development. Automated Bug Triage system is essential to reduce the cost and effort incurred by manual Bug Triage. At present, the metrics that are available in t...