Title :
CRF based Name Entity Recognition (NER) in Manipuri: A highly agglutinative Indian Language
Author :
Nongmeikapam, Kishorjit ; Shangkhunem, Tontang ; Chanu, Ngariyanbam Mayekleima ; Singh, Laishram Newton ; Salam, Bishworjit ; Bandyopadhyay, Sivaji
Author_Institution :
Dept. of Comput. Sc. & Eng., Manipur Univ., Imphal, India
Abstract :
This paper deals about the Name Entity Recognition (NER) of Manipuri, a highly agglutinative Indian Language. This language is an Eight Scheduled Language of Indian Constitution. NER plays an important role in the applications of Natural Language Processing like Machine Translation, Part of Speech tagging, Information Retrieval, Question Answering etc. Feature selection is an important factor in recognition of Manipuri Name Entity using Conditional Random Field (CRF). This model proved to have a Recall of 81.12%, Precision of 85.67% and F-Score of 83.33%.
Keywords :
natural language processing; F-score model; Indian language; Manipuri language; conditional random field; feature selection factor; information retrieval; machine translation; name entity recognition; natural language processing; part-of-speech tagging; precision model; question answering; recall model; Artificial neural networks; Hidden Markov models; Object recognition; Organizations; Tagging; Testing; Training; CRF; Manipuri; NER; feature; stem;
Conference_Titel :
Emerging Trends and Applications in Computer Science (NCETACS), 2011 2nd National Conference on
Conference_Location :
Shillong
Print_ISBN :
978-1-4244-9578-8
DOI :
10.1109/NCETACS.2011.5751390
