The enormous amount of information available today within different media gives rise to the notion of ways to reduce the inevitable complexity and to distribute text material to different channels or media. In an effort to investigate the possibilities of a tool to help eleviate the problem, an automatic summarizer called COGSUM has been developed and evaluated with regards to the informational quality of the summaries and with regards to the readability. COGSUM is based on word space methodology, including virtues such as problematic computational complexity and possibilities of inferring semantic relations. The results from the evaluations show how to set some parameters in order to get as good summary as possible and that the resulting summaries have higher readability score than the full text on different genres.
Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:liu-68332 |
Date | January 2011 |
Creators | Smith, Christian |
Publisher | Linköpings universitet, Institutionen för datavetenskap |
Source Sets | DiVA Archive at Upsalla University |
Language | English |
Detected Language | English |
Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
Format | application/pdf |
Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0025 seconds