Sequential Pattern Mining and Deep Learning to Enhance Readability of Indonesian Text Summarization

Abstract

Readability is a big challenge that must be solved in automatic text summarization research. The aim of this study is to comprehensively and systematically investigate the literatures that are related with text summarization needs, in particular, to prepare efficient algorithm for Indonesian text using Deep Learning and Sequential Pattern Mining. Evidence from previous literatures shows that there are several studies which use Sequential Pattern Mining to extract representation of text for document clustering and classification of Indonesian text. However, not much attention was given to text representation in document summarization, specifically for Indonesian language. As readability is a major concern in the text summarization community, determining a better text representation to maintain the meaning of the generated text summary is deemed necessary. This paper gives an opportunity to take a deeper look into how to design an efficient and effective text representation which can further enhance text summarization readability. Besides the general systematic literature review, we discuss an idea to combine Deep Learning and Sequential Pattern Mining to improve readability of summary result to develop in the future.

A Review of Textual and Voice Processing Algorithms in the Field of Natural Language Processing

“…This approach differs from the former, which utilizes the extracted text to construct a summary that appears more human-like in terms of grammar and structure. The implementation of automatic text summarization through a template-based approach involves a two-stage process, as described by Maylawati, Kumar, and Binti Kasmin [15].…”