DocumentCode
151497
Title
NER for Hindi language using association rules
Author
Jain, Abhishek ; Yadav, Divakar ; Tayal, Devendra Kr
Author_Institution
CSE/IT, JIIT, Noida, India
fYear
2014
fDate
5-6 Sept. 2014
Firstpage
1
Lastpage
5
Abstract
In this paper, we propose a state-of-art association rule mining algorithm for Hindi NER. Association rules are one of the key components of the data mining. Mined rules are of - TYPE 1, TYPE 2 and Type 3 i.e. dictionary, bi-gram and feature rules respectively. We consider corpus of news articles (100 training and 50 test sets) from leading Hindi newspapers. Hindi NER shows significant increase in performance when TYPE 2 rules are combined with TYPE 1 or with TYPE 3.
Keywords
data mining; natural language processing; publishing; Hindi NER; Hindi language; Hindi newspapers; association rule mining algorithm; bi-gram rules; data mining; dictionary rules; feature rules; mined rules; named entity recognition; natural language processing;; Association rules; Dictionaries; Natural language processing; Pragmatics; Text recognition; association rule; data mining; named entity; natural language processing;
fLanguage
English
Publisher
ieee
Conference_Titel
Data Mining and Intelligent Computing (ICDMIC), 2014 International Conference on
Conference_Location
New Delhi
Print_ISBN
978-1-4799-4675-4
Type
conf
DOI
10.1109/ICDMIC.2014.6954253
Filename
6954253
Link To Document