By Topic

Automatic document summarizer

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Harris, A. ; Dept. of Electron., Electr. & Comput. Eng., Univ. of Birmingham, Birmingham ; Oussalah, M.

The need for automatic summarization becomes crucial with the exponential increase of data available on www and digital libraries, which makes the search for relevant pieces of information a difficult task. Therefore, needless to say, an automatic summarizer would save a lot to user and operators. However, the development of such systems is also shown to be very challenging due to inherent difficulty in dealing with natural language processing, the subjectivity of the evaluation process and the limitation of the mathematical models. This paper puts forward a proposal for an automatic summarizer system, which explicitly makes use of the semantic relatedness of document sentences using WordNet taxonomy.On the other hand, several other attributes are taken into account in the design stage, which include similarity to user's query, if any, which allows us to integrate some personalization to the outcome, similarity to the document title, location and frequency of co-occurrence. The developed summarizer also enables some search abilities, where three distinct search platforms were integrated (Lucene, GTP and Xapian). The obtained results were compared to MEAD summarizer.

Published in:

Cybernetic Intelligent Systems, 2008. CIS 2008. 7th IEEE International Conference on

Date of Conference:

9-10 Sept. 2008