Difference between revisions of "Classifying Wikipedia Entities into Fine-Grained Classes"
(Starting a page: Classifying Wikipedia Entities into Fine-Grained Classes) |
(Wikilinks) |
||
| Line 1: | Line 1: | ||
| − | '''Classifying Wikipedia Entities into Fine-Grained Classes''' - scientific work related to Wikipedia quality published in 2011, written by Maksim Tkatchenko, Alexander Ulanov and Andrey Simanovsky. | + | '''Classifying Wikipedia Entities into Fine-Grained Classes''' - scientific work related to [[Wikipedia quality]] published in 2011, written by [[Maksim Tkatchenko]], [[Alexander Ulanov]] and [[Andrey Simanovsky]]. |
== Overview == | == Overview == | ||
| − | Recognition of named entities (people, companies, locations, etc) is an essential task of text analytics. Authors address the subproblem of this task, namely, named entity classification. Authors propose a novel approach that constructs an effective fine-grained named entity classifier. Its key highlights are semi-automatic training set construction from Wikipedia articles and additional feature selection. Authors justify solution by creating 18-class classifier and demonstrating its effectiveness and efficiency. | + | Recognition of [[named entities]] (people, companies, locations, etc) is an essential task of text analytics. Authors address the subproblem of this task, namely, [[named entity]] classification. Authors propose a novel approach that constructs an effective fine-grained named entity classifier. Its key highlights are semi-automatic training set construction from [[Wikipedia]] articles and additional feature selection. Authors justify solution by creating 18-class classifier and demonstrating its effectiveness and efficiency. |
Revision as of 23:06, 7 October 2019
Classifying Wikipedia Entities into Fine-Grained Classes - scientific work related to Wikipedia quality published in 2011, written by Maksim Tkatchenko, Alexander Ulanov and Andrey Simanovsky.
Overview
Recognition of named entities (people, companies, locations, etc) is an essential task of text analytics. Authors address the subproblem of this task, namely, named entity classification. Authors propose a novel approach that constructs an effective fine-grained named entity classifier. Its key highlights are semi-automatic training set construction from Wikipedia articles and additional feature selection. Authors justify solution by creating 18-class classifier and demonstrating its effectiveness and efficiency.
