An Approach to Summarize the Text Document to Retrieve Answers for Non-factoid Queries
Manjula A K
, Ramya R S , Dr Venugopal K R
Keywords: Summarize text document, Answer influenced summaries, document summarization, CQA data
ABSTRACT: This paper formulates a document summarization method which extracts the answers of passage size for non-factoid queries, which are referred as answer-influenced summaries. In this paper three methods are demonstrated for optimization they are question-biased, answer-biased CQA and extended question biased here extension terms are formulated from associated CQA data. The methods of ranking are also demonstrated which consists of features taken from CQA data. The quality of CQA data will affect the precision of the summary of optimization based. On the other hand the method of ranking is not much influenced by the quality of CQA. Suggestion is provided for the best use of the three optimization methods with respect to the different CQA quality of answers. In further research the accuracy is judged by other dataset which are open source. Most of the community information sharing website will contain answers which are shared according to user experience, these answers are collectively taken to find a better answer and one big answer will contain various information. The answers are used to expand the questions and answers among the search websites; this unique feature makes this approach for perfect answer generation.
"An Approach to Summarize the Text Document to Retrieve Answers for Non-factoid Queries", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.3, Issue 11, page no.407 - 415, November-2018, Available :https://ijsdr.org/papers/IJSDR1811072.pdf
Volume 3
Issue 11,
November-2018
Pages : 407 - 415
Paper Reg. ID: IJSDR_180856
Published Paper Id: IJSDR1811072
Downloads: 000347184
Research Area: Engineering
Country: Bengaluru Urban, Karnataka, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave