English

An HMM Based Named Entity Recognition System for Indian Languages: The JU System at ICON 2013

Computation and Language 2014-05-30 v1

Abstract

This paper reports about our work in the ICON 2013 NLP TOOLS CONTEST on Named Entity Recognition. We submitted runs for Bengali, English, Hindi, Marathi, Punjabi, Tamil and Telugu. A statistical HMM (Hidden Markov Models) based model has been used to implement our system. The system has been trained and tested on the NLP TOOLS CONTEST: ICON 2013 datasets. Our system obtains F-measures of 0.8599, 0.7704, 0.7520, 0.4289, 0.5455, 0.4466, and 0.4003 for Bengali, English, Hindi, Marathi, Punjabi, Tamil and Telugu respectively.

Keywords

Cite

@article{arxiv.1405.7397,
  title  = {An HMM Based Named Entity Recognition System for Indian Languages: The JU System at ICON 2013},
  author = {Vivekananda Gayen and Kamal Sarkar},
  journal= {arXiv preprint arXiv:1405.7397},
  year   = {2014}
}

Comments

The ICON 2013 tools contest on Named Entity Recognition in Indian languages (IL) co-located with the 10th International Conference on Natural Language Processing(ICON), CDAC Noida, India,18-20 December, 2013