Browse wiki

Jump to: navigation, search
Leveraging wikipedia characteristics for search and candidate generation in question answering
Abstract Most existing Question Answering (QA) systMost existing Question Answering (QA) systems adopt a type-and-generate approach to candidate generation that relies on a pre-defined domain ontology. This paper describes a type independent search and candidate generation paradigm for QA that leverages Wikipedia characteristics. This approach is particularly useful for adapting QA systems to domains where reliable answer type identification and type-based answer extraction are not available. We present a three-pronged search approach motivated by relations an answer-justifying title-oriented document may have with the question/answer pair. We further show how Wikipedia metadata such as anchor texts and redirects can be utilized to effectively extract candidate answers from search results without a type ontology. Our experimental results show that our strategies obtained high binary recall in both search and candidate generation on TREC questions, a domain that has mature answer type extraction technology, as well as on Jeopardy! questions, a domain without such technology. Our high-recall search and candidate generation approach has also led to high over-all QA performance in Watson, our end-to-end system. Copyright © 2011, Association for the Advancement of Artificial Intelligence. All rights reserved.ificial Intelligence. All rights reserved.
Abstractsub Most existing Question Answering (QA) systMost existing Question Answering (QA) systems adopt a type-and-generate approach to candidate generation that relies on a pre-defined domain ontology. This paper describes a type independent search and candidate generation paradigm for QA that leverages Wikipedia characteristics. This approach is particularly useful for adapting QA systems to domains where reliable answer type identification and type-based answer extraction are not available. We present a three-pronged search approach motivated by relations an answer-justifying title-oriented document may have with the question/answer pair. We further show how Wikipedia metadata such as anchor texts and redirects can be utilized to effectively extract candidate answers from search results without a type ontology. Our experimental results show that our strategies obtained high binary recall in both search and candidate generation on TREC questions, a domain that has mature answer type extraction technology, as well as on Jeopardy! questions, a domain without such technology. Our high-recall search and candidate generation approach has also led to high over-all QA performance in Watson, our end-to-end system. Copyright © 2011, Association for the Advancement of Artificial Intelligence. All rights reserved.ificial Intelligence. All rights reserved.
Bibtextype inproceedings  +
Has author Chu-Carroll J. + , Fan J. +
Has extra keyword Answer extraction + , Candidate generation + , Domain ontologies + , End-to-end systems + , Extraction technology + , QA system + , Question answering + , Question answering systems + , Search results + , Wikipedia + , Metadata + , Ontology + , Artificial intelligence +
Isbn 9781577355083  +
Language English +
Number of citations by publication 0  +
Number of references by publication 0  +
Pages 872–877  +
Published in Proceedings of the National Conference on Artificial Intelligence +
Title Leveraging wikipedia characteristics for search and candidate generation in question answering +
Type conference paper  +
Volume 1  +
Year 2011 +
Creation dateThis property is a special property in this wiki. 7 November 2014 23:35:13  +
Categories Publications without keywords parameter  + , Publications without license parameter  + , Publications without DOI parameter  + , Publications without remote mirror parameter  + , Publications without archive mirror parameter  + , Publications without paywall mirror parameter  + , Conference papers  + , Publications without references parameter  + , Publications  +
Modification dateThis property is a special property in this wiki. 7 November 2014 23:35:13  +
DateThis property is a special property in this wiki. 2011  +
hide properties that link here 
Leveraging wikipedia characteristics for search and candidate generation in question answering + Title
 

 

Enter the name of the page to start browsing from.