Difference between revisions of "Open-Domain Question Answering Framework Using Wikipedia"

From Wikipedia Quality
Jump to: navigation, search
(+ links)
(Infobox work)
 
Line 1: Line 1:
 +
{{Infobox work
 +
| title = Open-Domain Question Answering Framework Using Wikipedia
 +
| date = 2016
 +
| authors = [[Saleem Ameen]]<br />[[Hyunsuk Chung]]<br />[[Soyeon Caren Han]]<br />[[Byeong Ho Kang]]
 +
| doi = 10.1007/978-3-319-50127-7_55
 +
| link = https://link.springer.com/content/pdf/10.1007%2F978-3-319-50127-7_55.pdf
 +
}}
 
'''Open-Domain Question Answering Framework Using Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2016, written by [[Saleem Ameen]], [[Hyunsuk Chung]], [[Soyeon Caren Han]] and [[Byeong Ho Kang]].
 
'''Open-Domain Question Answering Framework Using Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2016, written by [[Saleem Ameen]], [[Hyunsuk Chung]], [[Soyeon Caren Han]] and [[Byeong Ho Kang]].
  
 
== Overview ==
 
== Overview ==
 
This paper explores the feasibility of implementing a model for an open domain, automated question and answering framework that leverages [[Wikipedia]]’s knowledgebase. While Wikipedia implicitly comprises answers to common questions, the disambiguation of natural language and the difficulty of developing an [[information retrieval]] process that produces answers with specificity present pertinent challenges. However, observational analysis suggests that it is possible to discount the syntactical and lexical structure of a sentence in contexts where questions contain a specific target entity (words that identify a person, location or organisation) and that correspondingly query a property related to it. To investigate this, authors implemented an algorithmic process that extracted the target entity from the question using CRF based [[named entity recognition]] (NER) and utilised all remaining words as potential properties. Using DBPedia, an ontological database of Wikipedia’s knowledge, authors searched for the closest matching property that would produce an answer by applying standardised string matching algorithms including the Levenshtein distance, similar text and Dice’s coefficient. Authors experimental results illustrate that using Wikipedia as a knowledgebase produces high precision for questions that contain a singular unambiguous entity as the subject, but lowered accuracy for questions where the entity exists as part of the object.
 
This paper explores the feasibility of implementing a model for an open domain, automated question and answering framework that leverages [[Wikipedia]]’s knowledgebase. While Wikipedia implicitly comprises answers to common questions, the disambiguation of natural language and the difficulty of developing an [[information retrieval]] process that produces answers with specificity present pertinent challenges. However, observational analysis suggests that it is possible to discount the syntactical and lexical structure of a sentence in contexts where questions contain a specific target entity (words that identify a person, location or organisation) and that correspondingly query a property related to it. To investigate this, authors implemented an algorithmic process that extracted the target entity from the question using CRF based [[named entity recognition]] (NER) and utilised all remaining words as potential properties. Using DBPedia, an ontological database of Wikipedia’s knowledge, authors searched for the closest matching property that would produce an answer by applying standardised string matching algorithms including the Levenshtein distance, similar text and Dice’s coefficient. Authors experimental results illustrate that using Wikipedia as a knowledgebase produces high precision for questions that contain a singular unambiguous entity as the subject, but lowered accuracy for questions where the entity exists as part of the object.

Latest revision as of 19:59, 14 June 2019


Open-Domain Question Answering Framework Using Wikipedia
Authors
Saleem Ameen
Hyunsuk Chung
Soyeon Caren Han
Byeong Ho Kang
Publication date
2016
DOI
10.1007/978-3-319-50127-7_55
Links
Original

Open-Domain Question Answering Framework Using Wikipedia - scientific work related to Wikipedia quality published in 2016, written by Saleem Ameen, Hyunsuk Chung, Soyeon Caren Han and Byeong Ho Kang.

Overview

This paper explores the feasibility of implementing a model for an open domain, automated question and answering framework that leverages Wikipedia’s knowledgebase. While Wikipedia implicitly comprises answers to common questions, the disambiguation of natural language and the difficulty of developing an information retrieval process that produces answers with specificity present pertinent challenges. However, observational analysis suggests that it is possible to discount the syntactical and lexical structure of a sentence in contexts where questions contain a specific target entity (words that identify a person, location or organisation) and that correspondingly query a property related to it. To investigate this, authors implemented an algorithmic process that extracted the target entity from the question using CRF based named entity recognition (NER) and utilised all remaining words as potential properties. Using DBPedia, an ontological database of Wikipedia’s knowledge, authors searched for the closest matching property that would produce an answer by applying standardised string matching algorithms including the Levenshtein distance, similar text and Dice’s coefficient. Authors experimental results illustrate that using Wikipedia as a knowledgebase produces high precision for questions that contain a singular unambiguous entity as the subject, but lowered accuracy for questions where the entity exists as part of the object.