|
Title:
|
AUTOMATIC CREATION OF LISTS FROM WIKIPEDIA ARTICLES |
|
Author(s):
|
Martin eleng and Ladislav Hluchý |
|
ISBN:
|
978-989-8533-95-1 |
|
Editors:
|
Hans Weghorn |
|
Year:
|
2019 |
|
Edition:
|
Single |
|
Keywords:
|
Wikipedia, Information Extraction, Automatic Extraction, Completion of Text Lists |
|
Type:
|
Full Paper |
|
First Page:
|
197 |
|
Last Page:
|
204 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
In the paper, we will introduce an approach to automatic list completion based on few keywords specified by the user, using
knowledge base constructed previously from English Wikipedia articles. Our approach is similar to Google Sets experiment
which does not exist nowadays but its part was integrated in Google Drive (formerly Google Docs) for some time. After
writing few words the system recommends additional words to create the list. Our solution is based on offline processing
of the English Wikipedia corpus where it searches for tables and lists (as a special case of one column table). These
tables/lists are indexed by the system and this index is used to extend user defined keywords by relevant items. |
|
|
|
|
|
|
