Kannada Stemmer and Its Effect on Kannada Documents Classification

N, Deepamala; Kumar, Pankaj

doi:10.1007/978-81-322-2202-6_7

Cited by 4 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The stemming algorithm used is a morphological stemmer [9] the algorithm uses rules of morphology and improves the stemming accuracy by analyzing the process of agglutination in Kannada. The morphological complexity of Kannada prevents direct suffix stripping as cited in [10]. The stemmer works efficiently on the concept of sub-sampling.…”

Section: Preprocessingmentioning

confidence: 99%

Multi-Classification and Automatic Text Summarization of Kannada News Articles

Anusha¹,

Uma²

2019

IJCA

View full text Add to dashboard Cite

Kannada is a historical language with abundant resources which display the tradition and culture of Karnataka. Extraction of most important and meaningful information from one or more large documents of text in the form of summary is a challenging task in regional languages compared to English. The main objective of present paper is to get the automatic summary of news articles from several sources. Naive-Bayes algorithm is used for classification of different categories of news articles include sports, politics and general. To find the sub-categories from each category such as state, national and international a Rock clustering algorithm has been used and the summary have been extracted automatically. Data is collected from multiple sources of summarization. A word vectorising stemmer approach is used to reduce the morphological complexity of the resources and a sub-sampling approach is used for efficient optimization and to reduce the complexity

show abstract

Section: Preprocessingmentioning

confidence: 99%