Multi-document Text Summarization in E-learning System for Operating System Domain

The query answering in E-learning systems generally mean retrieving relevant answer for the user query. In general the conventional E-learning systems retrieve answers from their inbuilt knowledge base. This leads to the limitation that the system cannot work out of its bound i.e. it does not answer for a query whose contents are not in the knowledge base. The proposed system overcomes this limitation by passing the query online and carrying out multi-document summarization on online documents. The proposed system is a complete E-learning system for the domain Operating systems. The system avoids the need to maintain the knowledge base thus reducing the space complexity. A similarity check followed by multi-document summarization leads to a non-redundant answer. The queries are classified into simple and complex types. Brief answers are retrieved for simple queries whereas detailed answers are retrieved for complex queries.

[1]  Cecilia R. Aragon,et al.  Randomized search trees , 1989, 30th Annual Symposium on Foundations of Computer Science.

[2]  Vagelis Hristidis,et al.  A system for query-specific document summarization , 2006, CIKM '06.

[3]  Lawrence O. Hall,et al.  Scalable clustering: a distributed approach , 2004, 2004 IEEE International Conference on Fuzzy Systems (IEEE Cat. No.04CH37542).

[4]  Behrouz A. Forouzan,et al.  Data Structures: A Pseudocode Approach with C , 2004 .

[5]  Liang He,et al.  Weighted Information Retrieval Algorithms for Onsite Object Service , 2007, 2007 International Multi-Conference on Computing in the Global Information Technology (ICCGI'07).

[6]  Walter Daelemans,et al.  Improving Accuracy in word class tagging through the Combination of Machine Learning Systems , 2001, CL.

[7]  Eugene Charniak,et al.  Statistical Techniques for Natural Language Parsing , 1997, AI Mag..

[8]  Bart De Moor,et al.  Evaluation of the Vector Space Representation in Text-Based Gene Clustering , 2002, Pacific Symposium on Biocomputing.

[9]  M.Z.H. Sarker,et al.  A Cost Effective Symmetric Key Cryptographic Algorithm for Small Amount of Data , 2005, 2005 Pakistan Section Multitopic Conference.

[10]  Nguyen Tuan Dang,et al.  Document Retrieval Based on Question Answering System , 2009, 2009 Second International Conference on Information and Computing Science.

[11]  Sung-Young Jung,et al.  Markov random field based English Part-Of-Speech tagging system , 1996, COLING.

[12]  S. Saraswathi,et al.  BiLingual Information Retrieval System for English and Tamil , 2010, ArXiv.

[13]  Padmini Srinivasan,et al.  A quality-threshold data summarization algorithm , 2008, 2008 IEEE International Conference on Research, Innovation and Vision for the Future in Computing and Communication Technologies.

[14]  Cecilia R. Aragon,et al.  Randomized search trees , 2005, Algorithmica.

[15]  R. Gunasekaran,et al.  Enhanced Cost Effective Symmetric Key Algorithm for Small Amount of Data , 2010, 2010 International Conference on Signal Acquisition and Processing.