Extractive Single Document Summarization
Text summarization is the process of distilling information from a source (or sources) to produce an abridged version for a particular user and task. Summarization methods can be grouped into two types: Extractive and Abstractive. Extractive methods identify relevant sentences within the document and concatenate them to form a summary. Abstractive methods rely on natural language generation to summarize the text and typically use a predefined template to be filled with information from the source text(s). In this work, we developed an extractive summarization system called Summarization Of Unstructured Papers (SOUP) for single document summarization.
The summarization package was developed by high-school students from Ms. Leonard's (aka Mrs. Tennessee) Hermitage Technical Center's Web Development & Programming Class:
Summarization Of Unstructured Papers (SOUP) -- A freely available open source extractive single document summarization system.
Last modified 19/08/2015