We present a working Arabic information extraction (IE) system that is used to analyze large volumes of news texts every day to extract the named entity types person, organization, location, date and number, as well as quotations (reported speech) by and about people. The NER system was not developed for Arabic, but - instead - a highly multilingual, almost language-independent NER system was adapted to also cover Arabic. Arabic substantially differs from the Indo-European and Finno-Ugric languages currently covered. This paper thus describes what Arabic language-specific resources had to be developed and what changes needed to be made to the otherwise language-independent rule set in order to be applicable to the Arabic language. The achieved evaluation results are generally satisfactory, but could be improved for certain entity types.
ZAGHOUANI Wajdi;
POULIQUEN Bruno;
EBRAHIM Mohamed;
STEINBERGER Ralf;
2010-06-07
European Language Resources Agency (ELRA)
JRC57133
http://www.lrec-conf.org/proceedings/lrec2010/index.html,
http://www.lrec-conf.org/proceedings/lrec2010/pdf/669_Paper.pdf,
https://publications.jrc.ec.europa.eu/repository/handle/JRC57133,
| Name | Country | City | Type |
|---|
This document is only visible at the Commission level.
You are not authorized to publish or distribute it outside the European Commission.
This is a public document. You can share this publication.
Datasets
| ID | Title | Public URL |
|---|
Dataset collections
| ID | Acronym | Title | Public URL |
|---|
Scripts / source codes
| Description | Public URL |
|---|
Additional supporting files
| File name | Description | File type |
|---|