Difference between revisions of "Summarizing with Wikipedia"

From Wikipedia Quality
Jump to: navigation, search
(New work - Summarizing with Wikipedia)
 
(wikilinks)
Line 1: Line 1:
'''Summarizing with Wikipedia''' - scientific work related to Wikipedia quality published in 2010, written by Abdullah Bawakid and Mourad Oussalah.
+
'''Summarizing with Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2010, written by [[Abdullah Bawakid]] and [[Mourad Oussalah]].
  
 
== Overview ==
 
== Overview ==
This paper describes a query-based multi-document summarizer that was built to participate in the update summarization task of TAC10. The system relies on a thesaurus extracted from Wikipedia and uses it as its underlying ontology. The concepts which are detected within the documents are used as weighted features to score the document sentences. The relationships previously defined in the thesaurus between the different concepts help in finding the most important concepts within a document or a set of documents. Sentences are ranked based on the scores they have been assigned and the summary is formed from the highest ranking sentences till the 100-word limit is reached. The evaluation results and the performance of the system are described. The system’s rank is the 7 in the manual evaluation of the update task for this year. The total number of the submitted runs by all participants is 43.
+
This paper describes a query-based multi-document summarizer that was built to participate in the update summarization task of TAC10. The system relies on a thesaurus extracted from [[Wikipedia]] and uses it as its underlying [[ontology]]. The concepts which are detected within the documents are used as weighted [[features]] to score the document sentences. The relationships previously defined in the thesaurus between the different concepts help in finding the most important concepts within a document or a set of documents. Sentences are ranked based on the scores they have been assigned and the summary is formed from the highest ranking sentences till the 100-word limit is reached. The evaluation results and the performance of the system are described. The system’s rank is the 7 in the manual evaluation of the update task for this year. The total number of the submitted runs by all participants is 43.

Revision as of 09:23, 12 August 2019

Summarizing with Wikipedia - scientific work related to Wikipedia quality published in 2010, written by Abdullah Bawakid and Mourad Oussalah.

Overview

This paper describes a query-based multi-document summarizer that was built to participate in the update summarization task of TAC10. The system relies on a thesaurus extracted from Wikipedia and uses it as its underlying ontology. The concepts which are detected within the documents are used as weighted features to score the document sentences. The relationships previously defined in the thesaurus between the different concepts help in finding the most important concepts within a document or a set of documents. Sentences are ranked based on the scores they have been assigned and the summary is formed from the highest ranking sentences till the 100-word limit is reached. The evaluation results and the performance of the system are described. The system’s rank is the 7 in the manual evaluation of the update task for this year. The total number of the submitted runs by all participants is 43.