期刊名称:International Journal of Advances in Engineering and Management
电子版ISSN:2395-5252
出版年度:2020
卷号:2
期号:10
页码:203-209
DOI:10.35629/5252-0210135138
语种:English
出版社:IJAEM JOURNAL
摘要:Natural Language Processing (NLP) is one of the interesting topics in the research field of Computer Science. Hindi is most precisely language spoke in India. POS tagging is a procedure in which we tag each word in a sentence present in a tagset. This paper presents Part of Speech Tagging for Hindi Language by using Rule Base Approach for proper tagging of words and CRF++ for training and testing the file and to calculate accuracy. The total dataset used for this implementation is 1530 words. The corpus is taken from various news, essays and stories. The system achieves an accuracy of 85.78%.
关键词:Natural Language Processing;Part of Speech;Rule base Approach;CRF++