A Multi Document Summarization of Learning Materials using Bigram Embedding Technique and Integer Linear Programming

Abstract

In the present era of the Internet, teachers and learners are heavily inclined to use e-learning systems for an efficient learning process. Due to the proliferation of educational text contents in these e-learning systems, the need for incorporating advanced text analysis tools and techniques are becoming inevitable. Multi Document Summarization (MDS) is a technique for producing concise summaries from a collection of related text documents. The usage of MDS in the context of e-learning is more promising for providing summaries for learning materials which helps students and teachers to focus on key concepts of the learning materials. In this paper a semantic approach towards the learning material summarization is proposed based on bigram embedding and ILP technique. This approach considers bigram as the basic meaningful semantic unit of the sentences to understand and summarize documents. Embedding techniques are employed to learn the vector representation of phrases to semantically identify similar phrases to reduce the redundancy and improving coherence. Using ILP technique, the summaries were generated by selecting important sentences while reducing the redundancy using phrase vectors. Experimental results on newly created educational dataset (EduSumm) shows better performance compared to the baseline systems.