Difference between revisions of "Relation-Based Wikipedia Search System Forfactoid Questions Answering"

From Wikipedia Quality
Jump to: navigation, search
(+ wikilinks)
(+ infobox)
Line 1: Line 1:
 +
{{Infobox work
 +
| title = Relation-Based Wikipedia Search System Forfactoid Questions Answering
 +
| date = 2014
 +
| authors = [[Adam Brzeski]]<br />[[Tomasz Boi´nski]]
 +
| link = http://www.rroij.com/open-access/relationbased-wikipedia-search-system-forfactoid-questions-answering.pdf
 +
}}
 
'''Relation-Based Wikipedia Search System Forfactoid Questions Answering''' - scientific work related to [[Wikipedia quality]] published in 2014, written by [[Adam Brzeski]] and [[Tomasz Boi´nski]].
 
'''Relation-Based Wikipedia Search System Forfactoid Questions Answering''' - scientific work related to [[Wikipedia quality]] published in 2014, written by [[Adam Brzeski]] and [[Tomasz Boi´nski]].
  
 
== Overview ==
 
== Overview ==
 
In this paper authors propose an alternative keyword search mechanism for [[Wikipedia]], designed as a prototype solution towards factoid questions answering. The method considers relations between articles for finding the best matching article. Unlike the standard Wikipedia search engine and also [[Google]] engine, which search the articles content independently, requiring the entire query to be satisfied by a single article, the proposed system is intended to solve queries by employing information contained in multiple articles. Although still a keyword search, the method can be further employed in natural language questions answering, when accompanied with a question processing module. The method assumes that queries are formulated in a form of a list of Wikipedia articles. The possible solutions are then evaluated, however not by attempting to understand the meaning of the text, but by a simple method of estimating the distance between articles by measuring articles’ references or appearances in other articles, leading finally to returning a single article as an answer for the query.
 
In this paper authors propose an alternative keyword search mechanism for [[Wikipedia]], designed as a prototype solution towards factoid questions answering. The method considers relations between articles for finding the best matching article. Unlike the standard Wikipedia search engine and also [[Google]] engine, which search the articles content independently, requiring the entire query to be satisfied by a single article, the proposed system is intended to solve queries by employing information contained in multiple articles. Although still a keyword search, the method can be further employed in natural language questions answering, when accompanied with a question processing module. The method assumes that queries are formulated in a form of a list of Wikipedia articles. The possible solutions are then evaluated, however not by attempting to understand the meaning of the text, but by a simple method of estimating the distance between articles by measuring articles’ references or appearances in other articles, leading finally to returning a single article as an answer for the query.

Revision as of 00:46, 10 November 2019


Relation-Based Wikipedia Search System Forfactoid Questions Answering
Authors
Adam Brzeski
Tomasz Boi´nski
Publication date
2014
Links
Original

Relation-Based Wikipedia Search System Forfactoid Questions Answering - scientific work related to Wikipedia quality published in 2014, written by Adam Brzeski and Tomasz Boi´nski.

Overview

In this paper authors propose an alternative keyword search mechanism for Wikipedia, designed as a prototype solution towards factoid questions answering. The method considers relations between articles for finding the best matching article. Unlike the standard Wikipedia search engine and also Google engine, which search the articles content independently, requiring the entire query to be satisfied by a single article, the proposed system is intended to solve queries by employing information contained in multiple articles. Although still a keyword search, the method can be further employed in natural language questions answering, when accompanied with a question processing module. The method assumes that queries are formulated in a form of a list of Wikipedia articles. The possible solutions are then evaluated, however not by attempting to understand the meaning of the text, but by a simple method of estimating the distance between articles by measuring articles’ references or appearances in other articles, leading finally to returning a single article as an answer for the query.