Difference between revisions of "Qast: Question Answering System for Thaiwikipedia"
(Overview: Qast: Question Answering System for Thaiwikipedia) |
(Int.links) |
||
| Line 1: | Line 1: | ||
| − | '''Qast: Question Answering System for Thaiwikipedia''' - scientific work related to Wikipedia quality published in 2009, written by Wittawat Jitkrittum, Choochart Haruechaiyasak and Thanaruk Theeramunkong. | + | '''Qast: Question Answering System for Thaiwikipedia''' - scientific work related to [[Wikipedia quality]] published in 2009, written by [[Wittawat Jitkrittum]], [[Choochart Haruechaiyasak]] and [[Thanaruk Theeramunkong]]. |
== Overview == | == Overview == | ||
| − | Authors propose an open-domain question answering system using Thai Wikipedia as the knowledge base. Two types of information are used for answering a question: (1) structured information extracted and stored in the form of Resource Description Framework (RDF), and (2) unstructured texts stored as a search index. For the structured information, SPARQL transformed query is applied to retrieve a short answer from the RDF base. For the unstructured information, keyword-based query is used to retrieve the shortest text span containing the questions's key terms. From the experimental results, the system which integrates both approaches could achieve an average MRR of 0.47 based on 215 test questions. | + | Authors propose an open-domain [[question answering]] system using Thai [[Wikipedia]] as the knowledge base. Two types of information are used for answering a question: (1) [[structured information]] extracted and stored in the form of Resource Description Framework (RDF), and (2) unstructured texts stored as a search index. For the structured information, SPARQL transformed query is applied to retrieve a short answer from the RDF base. For the unstructured information, keyword-based query is used to retrieve the shortest text span containing the questions's key terms. From the experimental results, the system which integrates both approaches could achieve an average MRR of 0.47 based on 215 test questions. |
Revision as of 16:15, 9 June 2019
Qast: Question Answering System for Thaiwikipedia - scientific work related to Wikipedia quality published in 2009, written by Wittawat Jitkrittum, Choochart Haruechaiyasak and Thanaruk Theeramunkong.
Overview
Authors propose an open-domain question answering system using Thai Wikipedia as the knowledge base. Two types of information are used for answering a question: (1) structured information extracted and stored in the form of Resource Description Framework (RDF), and (2) unstructured texts stored as a search index. For the structured information, SPARQL transformed query is applied to retrieve a short answer from the RDF base. For the unstructured information, keyword-based query is used to retrieve the shortest text span containing the questions's key terms. From the experimental results, the system which integrates both approaches could achieve an average MRR of 0.47 based on 215 test questions.
