• V.Meena
• S.Mohana priya
• V.Surya

The proposed system is going to deal with a very challenging task of automatically generating presentation slides for academic papers. The wide availability of web documents in electronic forms requires an automatic technique to label the documents with a predefined set of topics, what is known as automatic Text Categorization (TC). Over the past decades, it has been witnessed a large number of advanced machine learning algorithms to address this challenging task. The presenter prepares their formal slides with the help of generated presentation slide in a quicker way. Documents are usually represented by the “bag-of-words”: namely, each word or phrase occurs in documents once or more times is considered as a feature. It first employs the regression method to learn the importance scores of the sentences in an academic paper, and then an effective algorithm is developed for multilabel classification with utilizing those data that are relevant to the targets. The key is the construction of a coefficient-based mapping between training and test instances, where the mapping relationship exploits the correlations among the instances, rather than the explicit relationship between the variables and the class labels of data and manufactures the multilevel classifier on the adapted low-dimensional information portrayals at the same time. It initially utilizes the relapse technique to take in the significance scores of the sentences in a scholastic paper, and after that adventures the Latent Dirichlet Allocation (LDA) strategy to create very much organized slides by choosing and adjusting key expressions and sentences to a point for the slide. We prepare a sentence scoring model in light of naïve Bayes classifier and utilize the LDA technique to adjust and remove key expressions and sentences for producing the slides. Exploratory outcomes demonstrate that our strategy can produce much preferred slides over conventional strategies.

l1-norm, instance-based learning-nearest neighbors (kNNs),multilabel classification, partial least square(PLS) regression

"Slide Generation Approach Through Content Categorization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 3, page no.587-589, March-2018, Available :http://www.jetir.org/papers/JETIR1803107.pdf

"Slide Generation Approach Through Content Categorization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 3, page no. pp587-589, March-2018, Available at : http://www.jetir.org/papers/JETIR1803107.pdf