Interactive Intelligent Software System and NLP Techniques for Document Processing

  • Authors

    • Prashant G Desai
    • Sarojadevi H
    • Niranjan N Chiplunkar
    https://doi.org/10.14419/ijet.v7i3.34.19559
  • Artificial Intelligence, Conversation software, Dialogue, Summarization, Template based algorithm

  • The text written within the documents in different formats contains valuable information. Since the quantum of this kind of unstructured text to be processed is very large, a lot of research has taken place towards finding an intelligent system which helps in discovering the valuable information. The proposed research has developed a software system with the objective of processing natural language text and producing results of importance. This paper presents two new algorithms for document processing. The first algorithm interacts with users to find shorter answers using the query submitted by the user. The results show a precision of 80%. The second algorithm is based on the concept of a template prepared and input by the human. It is employed for representing the original document in a concise format.  The experimental results obtained and evaluated with the help of metrics from within the domain demonstrate that an accuracy of 73% can be achieved.

     

     

  • References

    1. [1] S.Brindha, K.Prabha and S.Sukumaran, “The comparison of term based methods using text miningâ€, Proceedings of International Journal of Computer Science and Mobile Computing , Vol. 5, Issue. 9, September 2016, pg.112 – 116

      [2] Gondy Leroy, Hsinchun Chen and Jesse D. Martinez, “A shallow parser based on closed-class words to capture relations in biomedical textâ€, Proceedings of Journal of Biomedical Informatics 36,2003, pp145–158

      [3] Fabrıcio Olivetti de Franca, “Scalable Overlapping Co-Clustering of Word-Document Dataâ€, Proceedings of 11th International Conference on Machine Learning and Applications,2012, pp 464-467

      [4] Jianguo Chen and Hao Chen “A Structured Information Extraction Algorithm for Scientific Papers based on Feature Rules Learningâ€, Proceedings of journal of software, vol. 8, no. 1, january 2013, pp55-62

      [5] Ioannis Hatzilygeroudis and Jim Prentzas, a “Using a hybrid rule-based approach in developing an intelligent tutoring system with knowledge acquisition and update capabilities†Proceedings of Expert Systems with Applications 26 , 2004, pp- 477–492

      [6] Raghu Anantharangachar, Srinivasan Ramani and S Rajagopalan, “ Ontology Guided Information Extraction from Unstructured Textâ€, Proceedings of International Journal of Web & Semantic Technology (IJWesT) Vol.4, No.1, January 2013, pp 19-36

      [7] R. Jayanthi and S. Sheela, “Domain Extraction From Research Papersâ€, Proceedings of Journal of Science and Technology (JST) Volume 2, Issue 4, April 2017, pp42-50

      [8] Yogendra Singh Rajput and Priya Saxena, “A Combined Approach for Effective Text Mining using Node Clusteringâ€, Proceedings of International Journal of Advanced Research in Computer and Communication Engineering Vol. 5, Issue 4, April 2016, pp321-324

      [9] Zhou Tong and Haiyi Zhang,“A text mining research based on LDA topic modelingâ€, Proceedings of Computer Science & Information Technology, 2016, pp 201–210

      [10] Ning Zhong, Yuefeng Li and Sheng-Tang Wu , “Effective Pattern Discovery for Text Miningâ€, Proceedings of IEEE transactions on knowledge and data engineering, Vol. 24, No. 1, January 2012, pp 30-44

      [11] D. Dubin, “The most influential paper Gerard Salton never wroteâ€, Library Trends 52(4), 2004, pp. 748–764

      [12] “PorterStemmerâ€, http://www.tartarus.org/~martin/PorterStemmer

      [13] Prashant G Desai, Sarojadevi, and Niranjan N Chiplunkar, “Rule-Knowledge Based Algorithm for Event Extractionâ€, Proceedings of International Journal of Advanced Research in Computer and Communication Engineering, ISSN : 2319-5940, Vol.4, Issue-1, January 2015, pp 79-85 , Impact Factor: 1.770

      [14] David Hawking and Nick Crasswell, “Measuring Search Engine Qualityâ€, Proceedings of Journal of Information Retrieval, 2000, pp1-27

      [15] Anna Huang, “Similarity Measures for Text Document Clusteringâ€, Proceedings of the New Zealand Computer Science Research Student Conference, 2008, pp 49-56

  • Downloads

  • How to Cite

    G Desai, P., H, S., & N Chiplunkar, N. (2018). Interactive Intelligent Software System and NLP Techniques for Document Processing. International Journal of Engineering & Technology, 7(3.34), 775-780. https://doi.org/10.14419/ijet.v7i3.34.19559