Arabic-L:LING:Broken Plural Evaluatoin Test Set Available

Dilworth Parkinson dilworthparkinson at GMAIL.COM
Wed Feb 19 16:01:18 UTC 2014


------------------------------------------------------------------------
Arabic-L: Wed 19 Feb 2014
Moderator: Dilworth Parkinson <dilworth_parkinson at byu.edu>
[To post messages to the list, send them to arabic-l at byu.edu]
[To unsubscribe, send message from same address you subscribed from to
listserv at byu.edu with first line reading:
           unsubscribe arabic-l                                      ]

-------------------------Directory------------------------------------

1) Subject: Broken Plural Evaluatoin Test Set Available

-------------------------Messages-----------------------------------
1)
Date: 19 Feb 2014
From: Alexis Neme <alexis.neme at gmail.com>
Subject: Broken Plural Evaluatoin Test Set Available

Dear Members,

We are pleased to announce that the evaluation test set for modelling the
broken plural  (cf. Neme, Laporte, 2013) is now available since February,
 5th and distributed with Unitex Corpus Processor

The 267 broken plurals with/without agglutinations can be obtained and
listed in a concordance.
The corpus has been preprocessed by Unitex with the PRIM dictionary of
broken plurals (Neme, Laporte, 2013) and Neme's (2011) dictionary of verbs.

We selected three documents totaling 3 550 tokens (about 10 pages) and
containing scientific popularization about three topics from the Nemlar
Corpus: pollution and fishing in Egypt, earthquakes, and quality of water.

During the construction of our lexicon of BPs, we did not use any part of
the corpus: our sources of information were handbooks, reference
dictionaries and native speaker competence. Thus, the evaluation tool is
independent from the evaluated resource.

- To access the annotated corpus, open Fishing-Earthquakes-Water.snt in the
Unitex/Arabic/Corpus. For more details,  see
readme_Fishing-Earthquakes-Water.txt in sub-directory Arabic\corpus) ....


Cheers

Alexis

Downloads
- Neme, Laporte, 2013. Pattern-and-Root Inflectional Morphology: the Arabic
broken plural (
https://www.researchgate.net/publication/254861185_Pattern-and-root_inflectional_morphology_the_Arabic_broken_plural?fulltextDialog=true&ev=prf_pub_xaddfulltext
)
- Unitex Corpus Processor (
http://www-igm.univ-mlv.fr/~unitex/zips/Unitex3.1beta.zip).

--------------------------------------------------------------------------
End of Arabic-L: 19 Feb 2014
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/arabic-l/attachments/20140219/cc2a16f4/attachment.htm>


More information about the Arabic-l mailing list