An Investigation Concerning the Generation of Text Summarisation Classifiers using Secondary Data

Abstract

An investigation into the potential effectiveness of generating text classifiers from secondary data for the purpose of text summarisation is described. The application scenario assumes a questionnaire corpus where we wish to provide a summary regarding the nature of the free text element of such questionnaires, but no suitable training data is available. The advocated approach is to build the desired text summarisation classifiers using secondary data and then apply these classifiers, for the purpose of text summarisation, to the primary data. We refer to this approach using the acronym CGUSD (Classifier Generation Using Secondary Data). The approach is evaluated using real questionnaire data obtained as part of the SAVSNET (Small Animal Veterinary Surveillance Network) project.