DESIGN OF A NOVEL SEARCH ENGINE FOR PROSPECTIVE QUESTION ANSWERING
Loading...
Date
item.page.authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The World Wide Web (WWW), the largest and most frequently accessed public repository of information ever developed, contains large number of web pages interconnected through hyperlinks. Search Engine is an information retrieval tool that provides a search interface to the people searching for some information, where he/she can submit his/her information need by writing queries. In response, the search engine returns relevant web pages in a ranked order by searching in repository maintained using the criterion of keyword matching. The pages with higher rank appear at the top and those at the bottom of the list are lower in rank.
newlineIf the user enters a question on the interface of the search engine, the search engine performs the same keyword matching approach and provides the list of web documents in ranked form. To find the answer to the question, the user has to go through the entire document. So, need of a system is felt which is capable of taking user s question as its input and return precise answer(s) as the output. Such a system is termed as a Question answering system. There are some major issues of concern that are found in the field of question answering as given below:
newline(i).Most of the existing systems for question answering takes the user s question as input and forwards it to the search engines like Google for the search results. The search results are the list of web pages returned to the user and the user has to go through the web page to find the answer.
newline(ii).There are some question answering systems that puts the question submitted by the user into the discussion forum and waits for the members of the forum to respond. The answers given by the members are then presented to the user in response to his question at the interface or via email.
newline(iii).It has been found that none of the previous work in this field typically focuses on all aspects associated with question answering i.e. crawling, summarization, question analysis, document representation, answer extraction or ranking.
newline