Optimized Text Summarization Methodology Using Hill Climbing Algorithm

Abstract

In this current scenario, the teaching and learning process has been supported by various electronic methods through the World Wide Web. The concepts made in short texts for understanding are always more ambiguous. Some of the online formative assessment activities for students are really helpful for the teachers to know about the grasping capacity of learners, which in turn is also used to tailor the next level accordingly. In spite of several teaching materials and methodologies, a learner expects to be recommended short passages or extracts of teaching records based on their needs. For efficient semantic analysis, few traditional methods are used for text segmentation, part-of-speech tagging, and concept labeling. Hence Summary recommendations are customized to students' needs according to the results of comprehension tests performed at the end of frontal lectures. In this paper, a new methodology referred as Hill Climbing algorithm-based text summarization approach for recommending summaries of potentially large teaching documents is proposed. Such that Hill Climbing word alignment is the natural language processing task of identifying translation relationships among the words in a bitext, resulting in a bipartite graph between the two sides of the bitext, with an arc between two words if and only if they are translations of one another. Word alignment is typically done after sentence alignment has already identified pairs of sentences. Specifically, students undergo multiple-choice tests through a mobile application. In parallel, a set of topic-specific summaries of the teaching documents is generated, which consist of the most significant sentences related to a specific topic. According to the results of the tests, summaries are personally recommended to students for a quick and easy way of enriching knowledge in a particular concept and thus show the optimal level among the traditional techniques.