Sentence extraction for summarization and Notetaking

Notetaking and summarization are important learning skills used by students, even when they are not explicitly instructed to do so. Summarization is the distillation of important information from a source into a shortened form for a particular user or task and Notetaking is to help students acquire and integrate knowledge. Fundamentally, notetaking is closely related to summarizing because it requires students to take information and synthesize it using their own words. In this research, we design both automatic summarization and semi-automatic notetaking system as important tools that can engage students in learning activity and improve their learning, namely comprehending and recalling of the study materials. However, they can be employed by lecturers to evaluate their student’s understanding. Many current systems summarize texts by selecting sentences with important content known as sentence extraction. To deal with the development of a new sentence extraction method, we delve into text analysis at three levels, such as word, sentence and text level analysis. At word level, we consider word similarity and word disambiguation based on WordNet to compute the value for semantic relatedness. This feature is exploited by the proposed method we have made for text similarity. For sentence Level, we analyse for its similarity using vector correlation. For text similarity, a cognitive method is used to identify the most important sentence. Proposed unsupervised sentence extraction method is then used to identify the most salient sentences to produce high quality summarization and notes.